Browse Source
[1.42.02]
git-svn-id: https://espeak.svn.sourceforge.net/svnroot/espeak/trunk@231 d46cf337-b52f-0410-862d-fd96e6ae7743master
jonsd
15 years ago
83 changed files with 3299 additions and 1637 deletions
+ 7
- 2
dictsource/da_list
View File
| @@ -1,4 +1,4 @@ | |||
| | |||
| // This file is UTF8 encoded | |||
| // Spelling-to-phoneme words for Danish | |||
| @@ -73,7 +73,7 @@ __ b'Onsdrai | |||
| ÷ divid'eReD meD | |||
| = l'imeD | |||
| # n'OmV | |||
| § paragr'af | |||
| § paragR'af | |||
| @@ -240,11 +240,16 @@ eget a:j@D | |||
| egne a:in@ | |||
| enter entV | |||
| ide id'e // idea | |||
| idé id'e // idea | |||
| igen igen | |||
| Ny ny // new | |||
| også Vs@ // also | |||
| havde h'aD@ // had | |||
| idet id'e // in so far as | |||
| sagde sa@ // said | |||
| sig sAi // oneself | |||
| //slags sl+ags // sort, type | |||
| tre tr'e // the number 3 | |||
+ 46
- 12
dictsource/da_rules
View File
| @@ -28,6 +28,7 @@ | |||
| au (K au | |||
| ch) au (f o | |||
| nive) au o | |||
| an (cienn aN | |||
| aw (K aw | |||
| ay (K aj | |||
| aa O: | |||
| @@ -106,10 +107,12 @@ | |||
| al) d (er | |||
| al) d (et | |||
| al) d (o d | |||
| al) d (rig d | |||
| an) d (re d | |||
| An) d (rA d | |||
| An) d (re d | |||
| be) d (A d | |||
| be) d (es D | |||
| bu) d (get | |||
| bu) d (t | |||
| ej) d (e d | |||
| @@ -123,6 +126,7 @@ | |||
| in) d (u d | |||
| in) d (uC d | |||
| in) d (ue d | |||
| la) d (t | |||
| le) d (t | |||
| li) d (e D | |||
| li) d (s D | |||
| @@ -148,12 +152,16 @@ | |||
| or) d (ning d | |||
| or) d (re d | |||
| or) d (ret | |||
| pu) d (s | |||
| pæ) d (a d | |||
| ro) d (s | |||
| ry) d (ni D | |||
| re) d (a d | |||
| re) d (i d | |||
| ri) d (e D | |||
| rø) dd (er D | |||
| si) d (e D | |||
| si) dd (e D | |||
| si) d (eA D | |||
| si) d (eC D | |||
| ti) d (e D | |||
| @@ -161,9 +169,11 @@ | |||
| ud) d d | |||
| ur) d (e d | |||
| ve) d (h D | |||
| ve) d (t D | |||
| vi) d (e D | |||
| vi) d (er D | |||
| yl) d (er | |||
| ær) d (es d | |||
| æl) d (e | |||
| æl) d (i d | |||
| æl) d (re d | |||
| @@ -173,10 +183,6 @@ | |||
| kla) dd (e D | |||
| kry) dd (er D | |||
| dd (et D | |||
| pu) d (s | |||
| ro) d (s | |||
| ry) d (ni D | |||
| ær) d (es d | |||
| bla) d (r D | |||
| dar) d d | |||
| gui) de d | |||
| @@ -189,6 +195,8 @@ | |||
| mad) d (A D | |||
| plu) d (se | |||
| ral) d (e | |||
| sag) d (e | |||
| sku) d (t | |||
| smu) d (s | |||
| snu) d (e D | |||
| Aor) d (ret d | |||
| @@ -215,6 +223,8 @@ | |||
| ver) d (en d | |||
| sli) d (so D | |||
| sli) d (s | |||
| skræ) dd (e D | |||
| kandi) d (at 'd | |||
| tilfre) d (s | |||
| @@ -229,14 +239,16 @@ tilfre) d (s | |||
| g) e (C e | |||
| g) e (js aj | |||
| em) e (nt a | |||
| plem) e (nter e | |||
| cem) e (nt e | |||
| elem) e (nt e | |||
| plem) e (nter e | |||
| em) e (ntal e | |||
| glem) e (nt a | |||
| glem) e (ntal e | |||
| ni) e | |||
| ni) e (n e | |||
| niv) e (au | |||
| bur) eau 'o | |||
| niv) eau 'o | |||
| ani) e (l e | |||
| lini) e e | |||
| r) e (_ V% | |||
| @@ -265,6 +277,8 @@ tilfre) d (s | |||
| en (gage aN | |||
| en (tre aN | |||
| c) en (t en | |||
| c) en (tA en | |||
| c) en (tC en | |||
| p) en (sion aN | |||
| r) en (ce aN | |||
| r) eg (n A:j | |||
| @@ -298,7 +312,7 @@ tilfre) d (s | |||
| ika) e (l | |||
| ir) e (n 'e | |||
| yr) e (n 'e | |||
| ompet) en (ce aN | |||
| .group f | |||
| @@ -352,6 +366,7 @@ tilfre) d (s | |||
| i) g (t_ | |||
| i) g | |||
| i) g (A | |||
| i) g (a g | |||
| i) g (en g | |||
| i) g (ere g | |||
| i) g (i g | |||
| @@ -376,12 +391,18 @@ tilfre) d (s | |||
| ø) g (e | |||
| ø) g (n | |||
| æ) g (e j | |||
| g (iv+ g // avoid letter "g" pronounced with phoneme S | |||
| Ca) g (en j | |||
| ha) g (l u | |||
| in) ge (niør Se | |||
| ki) gg (e g | |||
| la) g (C u | |||
| la) g (t g | |||
| la) gde e | |||
| li) g (ere | |||
| ra) g (_ w | |||
| ra) g (e w | |||
| sa) g (n u | |||
| ør) g (s | |||
| ur) g (A g | |||
| l) g (_ j | |||
| @@ -390,6 +411,8 @@ tilfre) d (s | |||
| li) g (g g | |||
| mA) g (a g | |||
| nA) g (a g | |||
| ta) g (A u | |||
| ta) g (C u | |||
| &e) g j | |||
| an) g (å g | |||
| ba) g (e | |||
| @@ -412,10 +435,13 @@ tilfre) d (s | |||
| sa) g (a =g | |||
| sa) g (s ' | |||
| si) g (t g | |||
| va) g (n u | |||
| pli) g (t g | |||
| &ti) g | |||
| bor) g u | |||
| bud) g (et S | |||
| gti) g | |||
| hol) g (er g | |||
| jer) g (A w | |||
| jer) g (C w | |||
| rea) g (er g | |||
| @@ -502,6 +528,7 @@ foreta) g (e | |||
| t) i (on // i ommitted because of sj | |||
| t) i (øs | |||
| s) i (on j | |||
| des) ign ain | |||
| ingen) i (ør | |||
| @@ -571,6 +598,7 @@ foreta) g (e | |||
| i) nd (eks nd | |||
| i) nd (ing n | |||
| u) nd ( n | |||
| bå) nd (A n | |||
| pu) n (kt | |||
| ru) n (ke | |||
| sa) n (kt | |||
| @@ -667,9 +695,8 @@ foreta) g (e | |||
| .group r | |||
| r r | |||
| b) r r | |||
| r (A R | |||
| ø) r V: | |||
| A) r r | |||
| Ae) r V | |||
| &) rd (e_ r | |||
| &) rd (eKK r | |||
| @@ -711,11 +738,13 @@ kompromi) s | |||
| &) tt t | |||
| &) th d | |||
| simpel) th (en th | |||
| t (ie t | |||
| t (ion+ sj' | |||
| t (iøs+ sj' | |||
| lek) t (i S | |||
| emen) t | |||
| cemen) t t | |||
| elemen) t t | |||
| emen) t (al t | |||
| glemen) t | |||
| @@ -733,21 +762,24 @@ glemen) t (al t | |||
| u (mK O | |||
| a) u (g u | |||
| b) u (dget y | |||
| b) u (reau y | |||
| g) ui (de ai | |||
| g) u (st O | |||
| l) u (k O? | |||
| l) u (kas u | |||
| m) u (k O? | |||
| r) u u | |||
| r) u (m O | |||
| r) u (nd O? | |||
| r) u (s u | |||
| s) u (cc y | |||
| comp) u (ter ju | |||
| fris) u (r y | |||
| frit) u (r y | |||
| men) u y | |||
| proced) u (re y | |||
| proven) u y | |||
| resso) u (rs 'u | |||
| g) u (st O | |||
| r) u (s u | |||
| s) u (cc y | |||
| .group v | |||
| @@ -859,3 +891,5 @@ glemen) t (al t | |||
+ 80
- 65
dictsource/de_list
View File
| @@ -23,9 +23,9 @@ _. pUnkt | |||
| € OY*o: | |||
| £ paUnd | |||
| & Unt | |||
| @ kl'ame:*,af@ | |||
| @ kl'am3_,af@ | |||
| ~ tIld@ | |||
| \ bEkslES | |||
| \ bakslaS | |||
| ° g@-*A:t | |||
| _, kOma | |||
| @@ -34,45 +34,46 @@ _: d'Op@lp,UNkt | |||
| _; St@-*'ICpUNkt | |||
| __ ,Unt3St@-*'IC | |||
| _- b'IndEst@-*,IC | |||
| _! 'aUs_|@-*,u:fe:ts,aIC@n | |||
| _? f@-*'Age:ts,aIC@n | |||
| _' 'apOst@-*,Of | |||
| _! 'aUs_|@-*,u:f@ts,aIC@n | |||
| _? f@-*'Ag@ts,aIC@n | |||
| _' ,apo:st@-*'Of | |||
| _" tsi:t'A:t | |||
| _/ S@-*'Egst@-*IC | |||
| _/ S@-*'e:gSt@-*IC | |||
| _( kl'am3||_|'aUf | |||
| _) kl'am3||ts'u: | |||
| _{ g@Sv'aIft@kl'am3||_|'aUf | |||
| _} g@Sv'aIft@kl'am3||ts'u: | |||
| _[ 'EkIg@kl'am3||_|'aUf | |||
| _] 'ECIg@kl'am3||ts'u: | |||
| _] 'EkIg@kl'am3||ts'u: | |||
| _< klaIn3 | |||
| _> g@-*Ws3 | |||
| _> g@-*Y:s3 | |||
| _` g@-*A:v | |||
| _^ sI*kUmflEks | |||
| _— g@d'ank@nSt@-*,IC | |||
| _^ tsI*kUmflEks | |||
| _— g@d'aNk@nSt@-*,IC | |||
| _#9 t,abu:l'Ato:* | |||
| _#9 t,abu:l'A:to:3 | |||
| _#32 l'e:*ts'aIC@n | |||
| _?? zymb'o:l | |||
| _?A b'UxstA:b@ | |||
| _?A b'u:xstA:b@ | |||
| _cap g@-*'o:s | |||
| // accent names | |||
| _lig l'i:gat,u:* | |||
| _lig l'i:gat,u:3 | |||
| _acu ak'u:t | |||
| _ac2 d'Op@l,aku:t | |||
| _brv b@-*'e:v@ | |||
| _ced tse:d'Il@ | |||
| _ac2 d'Op@lak,u:t | |||
| _brv b@-*'E:v@ | |||
| _ced se:d'i:j | |||
| _cir ts'I*kUmflEks | |||
| _dia 'UmlaUt | |||
| _dot p'Unkt | |||
| _grv g@-*'AvIs | |||
| _hac h'atSe:k | |||
| _mcn m'ak@-*o:n | |||
| _ogo 'o:go:n,e:k | |||
| _rng k@-*'u:Ze:k | |||
| _stk S@-*'Egst@-*IC | |||
| _grv g@-*'A:vIs | |||
| _hac h'atSEk | |||
| _mcn m'A:k@-*On | |||
| _ogo 'o:gOn,Ek | |||
| _rng k@-*'o:wZEk | |||
| _stk S@-*'e:gst@-*IC | |||
| _tld t'Ild@ | |||
| æ $accent | |||
| @@ -103,19 +104,19 @@ _10 'tse:n | |||
| _11 '_Elf | |||
| _12 'tsvWlf | |||
| _13 'd@-*aItse:n | |||
| _14 'fi:*tse:n | |||
| _14 'fI*tse:n | |||
| _15 'fynftse:n | |||
| _16 'zEktse:n | |||
| _16 'zECtse:n | |||
| _17 'zi:btse:n | |||
| _18 '_axttse:n | |||
| _18 '_axtse:n | |||
| _19 'nOYntse:n | |||
| _2X 'tsvantsIC | |||
| _3X 'd@-*aIsIC | |||
| _4X 'fi:*tsIC | |||
| _4X 'fI*tsIC | |||
| _5X 'fynftsIC | |||
| _6X 'zECtsIC | |||
| _7X 'zi:btsIC | |||
| _8X '_axttsIC | |||
| _8X '_axtsIC | |||
| _9X 'nOYntsIC | |||
| _0C 'hUnd3t | |||
| _0M1 'taUz@nt | |||
| @@ -131,7 +132,7 @@ _dpt _kOma | |||
| // ordinal numbers | |||
| _ord t@ // default ending | |||
| _ord20 st@ // 20,30,etc | |||
| _1o _'e:*st@ | |||
| _1o _'e:3st@ | |||
| _3o dr'It@ | |||
| _7o z'i:bt@ | |||
| _8o _'axt@ | |||
| @@ -139,15 +140,15 @@ _0Co 'hUnd3tst@ | |||
| // Abbreviations | |||
| //============== | |||
| a.a.o A:A:o: | |||
| allg 'alg@maIn@n | |||
| a.a.o A:||A:||_o: | |||
| allg 'alg@maIn | |||
| abb 'abb,IldUN | |||
| anm 'anm,E*kUN | |||
| bd band | |||
| bde bEnd@ | |||
| bzw b@tsi:hUNsvaIz@ | |||
| chr k@-*Istu:s | |||
| dm d'OYtSm,A:*k $capital $only $abbrev | |||
| bzw b@tsi:UNsvaIz@ | |||
| chr k@-*IstUs | |||
| dm d'OYtS@||m'A:*k $capital $only $abbrev | |||
| dr dOkt'o:* | |||
| evtl e:vEntu:'El | |||
| od o:d3 | |||
| @@ -155,7 +156,7 @@ fr f@-*aU | |||
| frl f@-*OYlaIn | |||
| hr hE* | |||
| hrsg hE*'aUsge:b3 | |||
| inkl Inklu:s'i:v@ | |||
| inkl Inklu:z'i:v@ | |||
| km ki:lo:me:t3 | |||
| nr nUm3 | |||
| st 'Este: | |||
| @@ -174,7 +175,7 @@ dem %de:m | |||
| des %dEs | |||
| derselb $2 | |||
| desselb dEss'Elb | |||
| desselb dEsz'Elb | |||
| dieselb $2 | |||
| dasselb dasz'Elb | |||
| demselb $2 | |||
| @@ -188,13 +189,13 @@ sondern $pause | |||
| denn dEn $u+ $pause | |||
| weil $pause | |||
| als $u+ $pause | |||
| bevor be:fo:* $2 $pause | |||
| bevor b@fo:* $2 $pause | |||
| also $pause | |||
| wenn ,vEn $pause $strend | |||
| sowie $2 $pause | |||
| obgleich $2 $pause | |||
| obwohl $2 $pause | |||
| deren dE*@n $u+ $brk | |||
| deren de:*@n $u+ $brk | |||
| // prepositions | |||
| ab ap $u+ $brk | |||
| @@ -218,7 +219,7 @@ in In $u+ $brk | |||
| im Im $u+ $brk | |||
| ins Ins $u+ $brk | |||
| mit mIt $u+ $pause | |||
| nach nax $u+ $brk | |||
| nach nA:x $u+ $brk | |||
| ob ,Ob $pause $strend $only | |||
| pro ,p@-*o: $pause | |||
| von fOn $u+ $brk | |||
| @@ -232,14 +233,14 @@ zur tsu:* $u+ $pause | |||
| unter ,Unt3 $pause $strend | |||
| um Um $u+ $brk | |||
| //(um die) %Umd%i: $brk | |||
| //(um den) %Umd%e:m $brk | |||
| //(um den) %Umd%e:n $brk | |||
| während $pause | |||
| // misc | |||
| so zo: $u+ | |||
| doch dOx $u+ | |||
| noch $pause | |||
| (noch nicht) n'Ox||n,ICt $brk | |||
| (noch nicht) n'Ox||n'ICt $brk | |||
| (nicht mehr) n'ICt||,me:* | |||
| (nicht mehr) n,ICt||m'e:* $atend | |||
| (nicht nur) n'ICt||n'u:* $pause | |||
| @@ -277,13 +278,13 @@ worin vo:*'In | |||
| ich IC $u $only | |||
| du du: $u $only | |||
| er Er $u $brk $only | |||
| es Ez $u $only | |||
| es Es $u $only | |||
| sie zi: $u $only | |||
| wir vi:* $u $only | |||
| ihr i:* $u | |||
| man man $u $only | |||
| sich zIC $u $only | |||
| (es ist) %Ez%Ist | |||
| (es ist) %Es%Ist | |||
| daß das $u+ | |||
| @@ -343,7 +344,7 @@ sind zInt $u | |||
| seit zaIt $u $only | |||
| habe %hA:b@ $only | |||
| habst %habst $only | |||
| habest hA:bEst $only $u | |||
| hast %hast $only | |||
| hat %hat $only | |||
| haben h,A:b@n $only | |||
| @@ -362,15 +363,15 @@ waren 'vA:*@n | |||
| will %vIl $only | |||
| willst %vIlst $only | |||
| wollen %vOl@n $only | |||
| wolt %vOlt | |||
| wollt %vOlt | |||
| werden v,E*d@n | |||
| werde v,E*d@ | |||
| werdst v,E*dst | |||
| wirst v,I*st | |||
| werdet v,E*d@t | |||
| wurden vU*d@n | |||
| wurde vU*d@ | |||
| wurdst vU*dst | |||
| wurdest v,U*dEst | |||
| wurdet vU*d@t | |||
| können ,kWn@n $only | |||
| @@ -396,6 +397,7 @@ account _^_EN | |||
| aid _^_EN // aids | |||
| appeal _^_EN | |||
| apple _^_EN | |||
| association _^_EN | |||
| baseball _^_EN | |||
| bbc _^_EN | |||
| beat _^_EN | |||
| @@ -410,9 +412,11 @@ computer _^_EN | |||
| cool _^_EN | |||
| couch _^_EN | |||
| cursor _^_EN | |||
| debugger _^_EN | |||
| dj _^_EN | |||
| email _^_EN | |||
| ensemble _^_FR | |||
| enterprise _^_EN | |||
| event _^_EN | |||
| firewall _^_EN | |||
| foul _^_EN | |||
| @@ -428,6 +432,7 @@ interface _^_EN | |||
| jean _^_EN | |||
| jet _^_EN | |||
| job _^_EN | |||
| joint _^_EN | |||
| joke _^_EN | |||
| joystick _^_EN | |||
| junkie _^_EN | |||
| @@ -439,6 +444,8 @@ look _^_EN | |||
| macho _^_EN | |||
| mail _^_EN | |||
| message _^_EN | |||
| my _^_EN | |||
| mysql _^_EN | |||
| offline _^_EN | |||
| online _^_EN | |||
| out _^_EN | |||
| @@ -467,6 +474,7 @@ slum _^_EN | |||
| small _^_EN | |||
| snob _^_EN | |||
| song _^_EN | |||
| source _^_EN | |||
| spam _^_EN | |||
| spirit _^_EN | |||
| squaw _^_EN | |||
| @@ -479,6 +487,7 @@ terminal _^_EN | |||
| trip _^_EN | |||
| tuner _^_EN | |||
| unix _^_EN | |||
| venture _^_EN | |||
| window _^_EN | |||
| word _^_EN | |||
| @@ -494,16 +503,17 @@ allein $2 | |||
| andre and@-*@ // andere | |||
| anomalie $2 | |||
| antik ant'i:k | |||
| archaik a*k'A:Ik | |||
| archaik a*C'A:Ik | |||
| arie $alt | |||
| arpeggier a*pEdZ'i:* | |||
| arrangier a*aNZ'i:@ | |||
| arterie $alt | |||
| asphalt $2 | |||
| atommüll $1 | |||
| ausgeschamt aUsg@SA:mt | |||
| außerdem aUs3d'e:m | |||
| außerdem 'aUs3d,e:m | |||
| aventurin avEntu:*'i:n | |||
| ave A:ve: | |||
| ave A:vE | |||
| balkan $1 | |||
| balkon $2 | |||
| @@ -521,6 +531,7 @@ ciao tSaU | |||
| coup ku: | |||
| dahlie $alt | |||
| debatte $2 | |||
| deshalb $2 | |||
| dezember $2 | |||
| diadem di:ad'e:m | |||
| @@ -533,13 +544,14 @@ duett du:'Et | |||
| ebendaher e:b@ndah'e:r | |||
| ebendahin e:b@ndah'In | |||
| ebenso $1 | |||
| einander aIn'and3 | |||
| einerlei aIn@*laI | |||
| einher aInh'e:r | |||
| einig aInIC $only | |||
| einige aInIg@ $u+ | |||
| einiges aInIg@s $u+ | |||
| enagier EngaZ'i:* | |||
| engagier aNgaZ'i:* | |||
| endivie $alt | |||
| endlich EntlIC | |||
| episkopal e:pIsko:p'A:l | |||
| @@ -548,7 +560,7 @@ erst e:*st | |||
| ersten e:*st@n | |||
| erstmal e:*stma:l | |||
| extravagant $1 | |||
| extrem Ekstr'e:m | |||
| extrem Ekst@-*'e:m | |||
| feuerrot $3 | |||
| friedvoll f@-*'i:tf,Ol | |||
| @@ -565,18 +577,17 @@ geranie ge:*'A:nI@ | |||
| gessen gEs@n | |||
| geste ge:st@ | |||
| gestern gEst3n | |||
| gestrig gEst@-*IC | |||
| glorie $alt | |||
| grazie $alt | |||
| handy handI | |||
| handy hEndi: | |||
| häuschen hOYsC@n | |||
| hausier haUz'i:* | |||
| heimat haImat | |||
| heimat $1 | |||
| herberg hE*bE*g | |||
| historie $alt | |||
| hm h@m | |||
| horsam ho:zA:m | |||
| horsam hO3zA:m | |||
| hostie $alt | |||
| illegitim Ile:gi:t'i:m | |||
| @@ -603,16 +614,14 @@ kanoe kan'u: | |||
| kastanie $alt | |||
| kid kId | |||
| komödie $alt | |||
| konkret k%ONk@-*e:t | |||
| konservativ $1 | |||
| konstatier kOnStat'i:* | |||
| konsul $1 | |||
| kurie $alt | |||
| lakaienhaft l%akaInhaft | |||
| lappalie $alt | |||
| lilie $alt | |||
| logier lo:Z'i:* | |||
| lucent lu:sEnt | |||
| luetisch lu:'e:tIS | |||
| machen max@n | |||
| @@ -621,7 +630,7 @@ materie $alt | |||
| menagier me:naZ'i:* | |||
| menuette mEnu:'Et | |||
| minut $2 | |||
| mikrofiche maIk@-*o:fIS | |||
| mikrofiche mi:k@-*o:fi:S | |||
| miteinander $1 | |||
| modell mo:d'El | |||
| monoton $3 | |||
| @@ -632,9 +641,10 @@ mumie $alt | |||
| nebulos $3 | |||
| negligent ne:gli:dZ'Ent | |||
| numero $1 | |||
| oberen o:b@*@n | |||
| oboe o:bo:@ | |||
| oboe o:b'o:@ | |||
| orgie $alt | |||
| ok o:k'e: | |||
| @@ -643,7 +653,7 @@ passage pas'aZ@ | |||
| perplex $2 | |||
| petersilie $alt | |||
| pinie $alt | |||
| planet plan'Et | |||
| planet plan'e:t | |||
| pochier pOS'i:* | |||
| pochs pOxs | |||
| präsident $3 | |||
| @@ -669,7 +679,7 @@ sowohl $2 | |||
| sparsam SpA:*zA:m | |||
| spinozaisch spi:n'o:tsaIS | |||
| stalagmit stalagm'It | |||
| system z%IstEm | |||
| system zIst'e:m | |||
| tag tA:g | |||
| telegen te:le:g'e:n | |||
| @@ -677,7 +687,6 @@ the D@ // English | |||
| theater te:'A:t3 | |||
| train t@-*e:n | |||
| turin $2 | |||
| tuerei tu:*aI | |||
| umweg $1 | |||
| unten Unt@n | |||
| @@ -694,13 +703,19 @@ vielleicht $2 | |||
| vorbei fo:*b'aI | |||
| vorher fo:*h'e:* | |||
| vorherig fo:*h'e:*IC | |||
| vorig fo:*IC | |||
| vorig fo:*Ig | |||
| //wahrscheinlich $2 | |||
| warum vA:*'Um | |||
| zoom zu:m | |||
| zuerst tsu:'E*st | |||
| //zuerst tsu:'E*st | |||
| zugegen tsu:g'e:g@n | |||
| zudem tsu:'de:m | |||
| zurück $2 | |||
| zymbal $1 | |||
| // Names | |||
| Neumexiko $2 | |||
| Neuseeland $2 | |||
+ 74
- 30
dictsource/de_rules
View File
| @@ -18,6 +18,7 @@ | |||
| // * <http://www.gnu.org/licenses/>. * | |||
| // ***************************************************************************/ | |||
| .L01 c f h k p q s t // unvoiced, except s+vowel | |||
| // This file is UTF-8 encoded | |||
| @@ -75,6 +76,7 @@ | |||
| _) animal ,ani:mA:l | |||
| _) anim ,ani:m | |||
| _) ani (s %ani: | |||
| a (Co_ 'A: | |||
| _) anti (@P4 ,antI | |||
| _) an (tw an | |||
| _) auf (@P3 _!'aUf | |||
| @@ -104,6 +106,7 @@ | |||
| air (_ E:r | |||
| akqu %akv | |||
| @A) al (_ 'A:l | |||
| b) al (_ 'A:l | |||
| g) al (_ 'A:l | |||
| k) al (_ 'A:l | |||
| n) al (_ 'A:l | |||
| @@ -129,6 +132,7 @@ | |||
| @) atisch (_S6 'A:tIS | |||
| @) atisieren (_S9 A:tIs'i:*@n | |||
| a (tion a | |||
| _) ato (m %ato: | |||
| _) au (Ceinand aU | |||
| _) aufent aUf@nt | |||
| austra (l %aUst@-*A | |||
| @@ -142,8 +146,8 @@ | |||
| b b | |||
| b) b | |||
| b (_N p | |||
| b (h p | |||
| b (s_ p | |||
| b (L01 p | |||
| b (sA b | |||
| bt (_N pt | |||
| _) be (@P2 b@ | |||
| @@ -212,14 +216,17 @@ | |||
| _) cey tsaI | |||
| chef SEf | |||
| _) c (ent ts | |||
| _) ch (ic S | |||
| _) ch (if S | |||
| _) ch (il S | |||
| chip (_ _^_EN | |||
| chip (_ tSIp // English | |||
| _) ch (ol k | |||
| _) ch (or k | |||
| bre) ch (en x | |||
| chro k@-*o: | |||
| nä) chs (t Cs | |||
| wa) chstu (m kstu: | |||
| c (ie s | |||
| pla) c (ie ts | |||
| coat (_ _^_EN | |||
| @@ -227,13 +234,15 @@ | |||
| _) cow _^_EN | |||
| crew _^_EN | |||
| cup _^_EN | |||
| _) cyber saIb3 | |||
| .group d | |||
| _) d (_ de: | |||
| d d | |||
| d) d | |||
| d (_N t | |||
| d (h t | |||
| d (L01 t | |||
| d (sA d | |||
| ds (_ ts | |||
| dt t | |||
| ddt t | |||
| @@ -310,6 +319,7 @@ | |||
| &) end (_ @nd | |||
| ier) end (_NS3 @nt | |||
| ier) end (_ @nd | |||
| @) enhaft (_ =@nhaft | |||
| @) ent (_ 'Ent | |||
| @) entlich @ntl%IC | |||
| @m) ent (_ 'Ent | |||
| @@ -331,7 +341,8 @@ | |||
| w) er (k_ E* | |||
| &) er (nd_ @* | |||
| &) erin (_ @*In | |||
| &) erisch (_ @*IS | |||
| &) erisch (_ @*IS | |||
| exp) er (t E* | |||
| @) es (_S2 @s | |||
| &) et (_S2 @t | |||
| &) est (_S3 @st | |||
| @@ -369,16 +380,19 @@ | |||
| _) emp (@P3 _|%Emp | |||
| _) emph (@ %Emf | |||
| _) emp (ir %Emp | |||
| br) ems Ems // brems-t, not brem-st | |||
| _) ene (rg %e:nE | |||
| _) energie e:nE*g'i: | |||
| @) en (i e:n | |||
| @) e (nsi E | |||
| _) ent (@P3 _|%Ent | |||
| _) enten Ent@n | |||
| _) ent (er Ent | |||
| pat) ent 'Ent | |||
| t) en (t En | |||
| qu) en (tA En | |||
| &) en (tum @n | |||
| &) e (nz_ 'E | |||
| &) e (nzK 'E | |||
| _) epi (@ ,e:pi: | |||
| _) epi (sk e:pI | |||
| _) er (@P2 _|%E* | |||
| @@ -387,6 +401,7 @@ | |||
| &) er (igst @* | |||
| _) er (beK E* | |||
| _) er (HC E* // lC, mC, nC, rC | |||
| er (o_ 'e:* | |||
| _) ergeb (nis E*g'e:b | |||
| _) er (stC E* | |||
| _) er (ste E* | |||
| @@ -431,9 +446,9 @@ | |||
| g g | |||
| g (g | |||
| g (_N k | |||
| g (h k | |||
| g (L01 k | |||
| g (sA g | |||
| gd (_N kt | |||
| gt (_N kt | |||
| gtet (_ kt@t | |||
| gtest kt@st | |||
| @@ -459,6 +474,7 @@ | |||
| _) ge (orP2 g@ | |||
| ge (rman gE | |||
| ge (rät g@ | |||
| ge (strig gE | |||
| @) ght (_ _^_EN | |||
| graph g@-*Af | |||
| graph (_ g@-*'A:f | |||
| @@ -564,6 +580,9 @@ | |||
| _) illeg ,Ile:g | |||
| _) i (llu %I | |||
| _) i (mag I | |||
| i (Co_ 'i: | |||
| ik (o_ i:k | |||
| &) im (o_ =i:m | |||
| r) i (na_ 'i: | |||
| // @) ing (_N _^_EN | |||
| _) in (k %In | |||
| @@ -603,6 +622,7 @@ | |||
| bank) ie (r I'e: | |||
| barr) ie (r I'e: | |||
| financ) ie (r I'e: | |||
| arr) ie (r I'e: | |||
| hotel) ie (r I'e: | |||
| prem) ie (r I'e: | |||
| hyg) ie (n I'e: | |||
| @@ -679,24 +699,24 @@ | |||
| _) leit (@P4 l'aIt | |||
| _) lern (@@P4 l'E*n | |||
| _) lexi (@ lEksi: | |||
| @) lich (_S4 lIC | |||
| @) liche (_S5 lIC@ | |||
| @) lichem (_S6 lIC@m | |||
| @) lichen (_S6 lIC@n | |||
| @) licher (_S6 lIC3 | |||
| @) liches (_S6 lIC@s | |||
| @) lichere (_S7 lIC@*@ | |||
| @) licherem (_S8 lIC@*@m | |||
| @) licheren (_S8 lIC@*@n | |||
| @) licherer (_S8 lIC@*@3 | |||
| @) licheres (_S8 lIC@*@s | |||
| @) lichste (_S7 lICst@ | |||
| @) lichstem (_S8 lICst@m | |||
| @) lichsten (_S8 lICst@n | |||
| @) lichster (_S8 lICst@r | |||
| @) lichstes (_S8 lICst@s | |||
| @) lichkeit (_S8 lICk%aIt | |||
| @) lichung (_S7 lIC%UN | |||
| &) lich (_S4 lIC | |||
| &) liche (_S5 lIC@ | |||
| &) lichem (_S6 lIC@m | |||
| &) lichen (_S6 lIC@n | |||
| &) licher (_S6 lIC3 | |||
| &) liches (_S6 lIC@s | |||
| &) lichere (_S7 lIC@*@ | |||
| &) licherem (_S8 lIC@*@m | |||
| &) licheren (_S8 lIC@*@n | |||
| &) licherer (_S8 lIC@*@3 | |||
| &) licheres (_S8 lIC@*@s | |||
| &) lichste (_S7 lICst@ | |||
| &) lichstem (_S8 lICst@m | |||
| &) lichsten (_S8 lICst@n | |||
| &) lichster (_S8 lICst@r | |||
| &) lichstes (_S8 lICst@s | |||
| &) lichkeit (_S8 lICk%aIt | |||
| &) lichung (_S7 lIC%UN | |||
| @) lo (gisch l'o: | |||
| .group m | |||
| @@ -760,6 +780,8 @@ | |||
| o (sch O | |||
| o (x O | |||
| &CC) o (_ =o: | |||
| o (Co_ 'o: | |||
| o (lo_ o: | |||
| ob (t_ o:p | |||
| og (t_ o:k | |||
| @@ -793,6 +815,7 @@ | |||
| pf pF | |||
| ph f | |||
| pake (t p%ake: | |||
| _) para (@ p,a*a | |||
| passagie pasaZ'i: | |||
| _) peri p,e:*i: | |||
| @@ -859,6 +882,9 @@ | |||
| _be) sp Sp | |||
| _ge) sp Sp | |||
| _ver) sp Sp | |||
| sp (eich Sp | |||
| sp (err Sp | |||
| sp (r Sp | |||
| &C) st (_S2 st | |||
| &C) ste (_S3 st@ | |||
| &C) stem (_S4 st@m | |||
| @@ -870,6 +896,8 @@ | |||
| _be) st St | |||
| _ge) st St | |||
| _ver) st St | |||
| ste (ll StE | |||
| a) ste (ll stE | |||
| _) safe _^_EN | |||
| &) schaft (_S6 Saft | |||
| @@ -892,6 +920,7 @@ | |||
| schwer Sve:* | |||
| _) sechs (P5 z'Eks | |||
| _) selbst (@@P6 z'Elpst | |||
| service (_S7 z%Ervi:s | |||
| shop _^_EN | |||
| _) sky _^_EN | |||
| soldat z%OldA:t | |||
| @@ -899,6 +928,7 @@ | |||
| sound _^_EN | |||
| speed _^_EN | |||
| stau) ss s | |||
| @) straße (_S6 st*,A:s@ | |||
| _) street _^_EN | |||
| style _^_EN | |||
| @@ -940,10 +970,12 @@ | |||
| ier) tester (_S6 t@st3 | |||
| ier) testes (_S6 t@st@s | |||
| _) talent tal'Ent | |||
| tch tS | |||
| t (chen_ t | |||
| _) teen _^_EN | |||
| _) tele (@ t,e:le: | |||
| tuerei (_ tu:@*'aI | |||
| thrill _^_EN | |||
| _pa) th t | |||
| the (era te: | |||
| @@ -1042,12 +1074,18 @@ | |||
| _) v (on f | |||
| _) vehe ve:he: | |||
| _) ver (@P3 f%E* | |||
| _) ver (bal v%E* | |||
| _) ver (sion vE* | |||
| _) ver (tik vE* | |||
| _) ver (@P3 f%Er | |||
| _) ve (rbal vE | |||
| _) ve (rbos v%E | |||
| _) ve (rsat vE | |||
| _) ve (rsie vE | |||
| _) ve (rsif vE | |||
| _) ve (rsion vE | |||
| _) ve (rteb vE | |||
| _) ve (rtik vE | |||
| @) versich fE*z,IC | |||
| @) vergess fE*g,Es | |||
| @) verfahren (_S9 fErf,A:@-*@n | |||
| _) viel (@P4 f'i:l | |||
| _) vier (g@P4 f'i:* | |||
| _) viet vIEt | |||
| @@ -1080,6 +1118,8 @@ | |||
| _) weg (C@P3 v'e:k | |||
| _) weit (C@P4 v'aIt | |||
| _) weiter (@P6 v'aIt@* | |||
| _) weither vaIthe:* | |||
| _) wieder (@P6 vi:d3 | |||
| _) wo (hin v%o: | |||
| _) wohl (@P4 v'o:l | |||
| work _^_EN | |||
| @@ -1119,6 +1159,9 @@ | |||
| _) zigaretten (@P10 tsi:ga*'Et@n | |||
| _) zigeu tsi:g'OY | |||
| _) zu (C@P2 ts%u: | |||
| _) zu (eP2 ts%u: | |||
| _) zu (g@ tsu: | |||
| _) zu (gu@P2 ts%u: | |||
| _) zu (nC tsU | |||
| _) zurück (@P6 tsu:*'yk | |||
| _) zyklo (@P5 ,tsy:klo: | |||
| @@ -1136,6 +1179,7 @@ | |||
| äb (t_ E:p | |||
| äg (t_ E:k | |||
| t) ät (_ 'E:t | |||
| ä (um_N 'E: | |||
| .group ö | |||
| ö Y: | |||
+ 24
- 22
dictsource/dict_phonemes
View File
| @@ -107,10 +107,10 @@ Dictionary en_dict | |||
| 0 3 3: @ @- @2 @5 @L | |||
| a a2 A: A@ aa aI aI@ aU | |||
| aU@ A~ E e@ eI I i I2 | |||
| i: i@ i@3 IR O O: o: O@ | |||
| o@ OI oU O~ U u: U@ V | |||
| VR | |||
| aU@ A~ E e: e@ eI I i | |||
| I2 i: i@ i@3 IR O O: o: | |||
| O@ o@ OI oU O~ U u: U@ | |||
| V VR | |||
| : ; ? b C d D dZ | |||
| f g g- h j k l L | |||
| @@ -221,10 +221,10 @@ Dictionary hu_dict | |||
| A a: E e: i i: o o: | |||
| u u: Y y y: Y: | |||
| : b c C d dZ f g | |||
| h j J k l l^ m n | |||
| N n^ p R R2 s S s2 | |||
| t tS ts v z Z | |||
| - : b c d dZ f g | |||
| h j J k l m n n^ | |||
| p r R R2 s S s2 t | |||
| tS ts v z Z | |||
| Dictionary hy_dict | |||
| @@ -292,9 +292,9 @@ y | |||
| : b bh c ch d d. dh | |||
| dh. dZ f g gh h j J | |||
| Jh k kh l l. m n N | |||
| n. n^ p ph R R2 s S | |||
| s. S; t t. th th. tS v | |||
| w z | |||
| n. n^ p ph r R R2 s | |||
| S s. S; t t. th th. tS | |||
| v w z | |||
| Dictionary ku_dict | |||
| @@ -445,9 +445,11 @@ tS; v w x z Z Z; | |||
| Dictionary prs_dict | |||
| @ A i o | |||
| @ A E eI i o u | |||
| b d h l t X | |||
| : b d dZ f g h j | |||
| k l m n p r R s | |||
| S t tS v w X z Z | |||
| Dictionary pt_dict | |||
| @@ -471,12 +473,12 @@ ea eI eo eU i i/ I^ iI | |||
| iU o O Oa oI oU u uI | |||
| y Y yI yU | |||
| * *; - b b; c C d | |||
| d; dZ f f; g h j k | |||
| l l; m m; n N n; p | |||
| p; r s S S; t t; tS | |||
| ts ts; v v; w w2 x z | |||
| Z z; Z; | |||
| * *; b b; c C d d; | |||
| dZ f f; g h j k l | |||
| l; m m; n N n; p p; | |||
| r s S S; t t; tS ts | |||
| ts; v v; w w2 x z Z | |||
| z; Z; | |||
| Dictionary ru_dict | |||
| @@ -558,9 +560,9 @@ I i: o o: U u u: V | |||
| : ; b C d d. dZ f | |||
| g h H j k l l. m | |||
| n N n. n^ p r R s | |||
| S s. t t. th tS v w | |||
| z z. | |||
| n N n. n^ p Q r R | |||
| s S s. t t. th tS v | |||
| w z z. | |||
| Dictionary tr_dict | |||
+ 33
- 16
dictsource/en_list
View File
| @@ -98,7 +98,7 @@ _?A l,Et3 | |||
| _?? sImb@L | |||
| _#9 tab | |||
| _#32 speIs | |||
| … _::d%0td,0t // for elipsis or ... while reading | |||
| //… _::d%0td,0t // for elipsis or ... while reading | |||
| _ hA@dspeIs // U+00A0 no-break-space | |||
| _! Ekskl@m'eIS@n | |||
| @@ -181,10 +181,8 @@ _₠ jU@roU | |||
| # haS $max3 | |||
| @ _at_ $u+ | |||
| & _and $u+ | |||
| \ bakstroUk $max3 | |||
| / stroUk $max3 | |||
| ?3 \ bakslaS $max3 | |||
| ?3 / slaS $max3 | |||
| \ bakslaS $max3 | |||
| / slaS $max3 | |||
| * ast@rIsk $max3 | |||
| % p3sEnt $max3 | |||
| ?5 % pVRs'Ent $max3 | |||
| @@ -346,11 +344,11 @@ ctrl k0ntr'oUl | |||
| dept dI2pA@tm@nt | |||
| diy $abbrev | |||
| edt $abbrev | |||
| eg fO@Egz'aamp@L | |||
| eg fO@Egz'aamp@L $only | |||
| est $abbrev | |||
| etc Et'sEtr@ | |||
| eu $abbrev | |||
| eur jU@ | |||
| eur jU@ $only | |||
| hmm h@m | |||
| (http ://) eItSti:ti:'pi:_ | |||
| ibm $abbrev | |||
| @@ -362,6 +360,7 @@ lbs paUndz | |||
| LBS $abbrev | |||
| ltd lImI2tI2d | |||
| mc m@k $combine // combine with the following word | |||
| mya $abbrev | |||
| ny $abbrev | |||
| oem $abbrev | |||
| ok $abbrev | |||
| @@ -506,6 +505,7 @@ albeit O:lb'i:It | |||
| alfalfa alf'alf@ | |||
| alias eIli@s | |||
| alibi al@baI | |||
| alibis al@baIz | |||
| alkali alk@laI | |||
| allay a2leI | |||
| allegiance a2li:dZ@ns | |||
| @@ -598,6 +598,7 @@ archimedes A@kIm'i:di:z | |||
| archive A@kaIv | |||
| archway $1 | |||
| arena a2ri:n@ | |||
| argue A@gju: | |||
| arithmetic a2rITm@tIk | |||
| arise a2raIz | |||
| arisen a2rIz@n | |||
| @@ -739,7 +740,6 @@ campus kamp@s // campuses | |||
| canal k@nal | |||
| canary k@ne@rI | |||
| canine keInaIn | |||
| cannabis kana2bIs | |||
| canoe k@nu: | |||
| canoes k@nu:z | |||
| canton kant0n | |||
| @@ -781,6 +781,7 @@ chemise SEm'i:z | |||
| chic Si:k | |||
| chimpanzee $3 | |||
| chisel tSIz@L | |||
| chloroplast $1 | |||
| chocolate tS0kl@t | |||
| cholera k0l@r@ | |||
| cholesterol k@lEst@r0l | |||
| @@ -1048,6 +1049,7 @@ eras i@r@z | |||
| erase I2reIz // erasing erases | |||
| ere e@ $only | |||
| eros i@r0s | |||
| err 3: | |||
| errand Er@nd | |||
| escapism Esk'eIpI2z@m | |||
| escargot I2sk'A@goU | |||
| @@ -1157,6 +1159,7 @@ furthermore f3:D3m'o@ $pause | |||
| ?5 furthermore fVRD3m'o@ $pause | |||
| fuscia fju:S@ | |||
| fuselage fju:z@lA:Z | |||
| futon fu:t0n | |||
| gala gA:l@ | |||
| galaxy gala2ksI | |||
| @@ -1210,6 +1213,7 @@ havoc hav@k | |||
| hasty heIstI | |||
| hatred heItrI2d | |||
| hazardous haz3d@s | |||
| heh hEh | |||
| hehe hi:h'i: | |||
| heifer hEf@ | |||
| heist haIst | |||
| @@ -1349,6 +1353,7 @@ july dZu:l'aI | |||
| kaput ka2pUt | |||
| karate k@rA:tI | |||
| kebab k@bab | |||
| kefir ki:f3 | |||
| hiatus haI'eIt@s | |||
| kilo ki:loU | |||
| kilter kIlt3 | |||
| @@ -1382,7 +1387,7 @@ leant lEnt | |||
| leapt lEpt | |||
| lego lEgoU | |||
| leisure l'EZ3 | |||
| lemme lElI // let me | |||
| lemme lEmI // let me | |||
| lemonade $3 | |||
| leo li:oU | |||
| leopard lEp@d | |||
| @@ -1390,6 +1395,7 @@ lesion li:Z@n | |||
| lethal li:T@L | |||
| liaison li:'eIz0n | |||
| libre li:br@ | |||
| lichen laIk@n | |||
| lier laI3 // outlier | |||
| ligate li:geIt | |||
| lilac laIl@k | |||
| @@ -1503,7 +1509,8 @@ mitre maIt3 | |||
| mixer mIks3 | |||
| modem moUdEm | |||
| moderate m0d@reIt $verb | |||
| momentum $2 | |||
| momentary moUm@nt@rI | |||
| momentum $2 | |||
| monday mVndeI | |||
| monotone m0n@toUn | |||
| monsieur m@sj3: | |||
| @@ -1603,6 +1610,7 @@ orion 0r'aI@n | |||
| ordeal O@d'i@l | |||
| orphan O@f@n // orphaned | |||
| outage $1 | |||
| outback $1 | |||
| outcome $1 | |||
| outer aUt3 | |||
| outbreak $1 | |||
| @@ -1612,13 +1620,16 @@ outcrop $1 | |||
| outcry $1 | |||
| outed aUtI2d | |||
| outfit $1 | |||
| outhouse $1 | |||
| outing $1 | |||
| outlaw $1 | |||
| outlay $1 | |||
| outlet $1 | |||
| outlier 'aUtl,aI3 | |||
| outline $1 | |||
| outlive aUtl'Iv | |||
| outlook $1 | |||
| outmost $1 | |||
| outpost aUtpoUst | |||
| output $1 | |||
| outrage $1 | |||
| @@ -1786,6 +1797,7 @@ question kwEstS@n | |||
| quiche ki:S | |||
| quiver kwIv3 | |||
| rabbis rabaIz | |||
| rabid reIbI2d | |||
| radar reIdA@ | |||
| radioactive reIdI2oU'aktIv | |||
| @@ -1925,8 +1937,6 @@ saucepan sO:sp@n | |||
| saudi saUdI | |||
| saute sO:teI | |||
| says sEz | |||
| schema ski:m@ | |||
| shallow SaloU | |||
| salmon sam@n | |||
| scalpel skalp@L | |||
| scared ske@d | |||
| @@ -1972,10 +1982,12 @@ severe sI2v'i@3 $only | |||
| severely sI2v'i@3lI2 $verbf | |||
| sex sEks // sexism | |||
| several sEvr@L | |||
| shallow SaloU | |||
| shampoo $2 | |||
| sheriff S'ErI2f | |||
| shew SoU | |||
| shia Si:@ | |||
| shiitake Si:t'A:ke: | |||
| shillelagh S,I2l'eIl@ | |||
| shiver SIv3 | |||
| shone S0n | |||
| @@ -2293,7 +2305,7 @@ yoghurt j0g3t | |||
| ?3 yoghurt joUg3t | |||
| yoyo joUjoU | |||
| zulu zu:lu: | |||
| zulus zu:lu:z | |||
| // place names | |||
| @@ -2580,6 +2592,7 @@ Cheri Se@r'i: | |||
| Cherie Se@r'i: | |||
| Chloe kloUI | |||
| Chris krIs | |||
| Cleo kli:oU | |||
| Connie k0nI | |||
| Connor k0n3 | |||
| Daphne dafnI | |||
| @@ -2786,6 +2799,7 @@ of 0v $u $only | |||
| (of a) @v@ $nounf | |||
| (of an) @v@n $nounf | |||
| (of which) 0vwItS $2 $pause | |||
| (of the) %0vD@2 $nounf | |||
| ?6 (of the) %VD@2 $nounf | |||
| ?6 (of which) VvwItS $2 $pause | |||
| @@ -2834,7 +2848,7 @@ from fr0m $u | |||
| (from which) %fr0m||w'ItS $pause | |||
| up ,Vp $strend2 | |||
| down ,daUn $only $strend2 | |||
| by baI $u | |||
| by baI $u+ | |||
| across @kr0s $u2 $strend2 | |||
| per p3: $u | |||
| (per cent) p3||s'Ent | |||
| @@ -2866,7 +2880,7 @@ thence DEns | |||
| //aux. verbs | |||
| be %bi: $pastf $only | |||
| be bi: $pastf $only $u+ | |||
| been ,bi:n $pastf $only | |||
| ?3 been ,bIn $pastf $only | |||
| being ,bi:IN $pastf $only $strend2 | |||
| @@ -2939,7 +2953,7 @@ might ,maIt $verbf $strend2 $only | |||
| (might have) maItha2v $pastf $u1+ | |||
| (might have to) ,maIth'avt@5 $verbf $atend | |||
| have %hav $pastf $only $strend2 | |||
| have hav $pastf $only $u $strend2 | |||
| haves havz | |||
| (have been) %hav%bIn $pastf | |||
| has %ha2z $pastf $only | |||
| @@ -2979,6 +2993,9 @@ did dId $verbf | |||
| didn't dIdnt $verbf | |||
| done dVn | |||
| make m,eIk $strend2 $only | |||
| made m,eId $strend2 $only | |||
| putting pUtI2N | |||
| put ,pUt $onlys $strend2 | |||
+ 88
- 70
dictsource/en_rules
View File
| @@ -495,6 +495,7 @@ | |||
| al (ien eIl | |||
| _) al (i al | |||
| _) al (ig a2l | |||
| X) al (in eIl | |||
| _) ali (Be a2laI | |||
| &) ali (sC_ @lI | |||
| &) al (isCic @l | |||
| @@ -628,6 +629,7 @@ | |||
| amaz (o am@z | |||
| ambi (d ambI | |||
| ch) am (b eIm | |||
| ambiv amb'Iv | |||
| fl) ame eIm | |||
| As) ame (_ 'A:mE | |||
| _) ame (l a2mi: | |||
| @@ -733,6 +735,7 @@ | |||
| ch) ang (e eIndZ | |||
| ch) anging eIndZIN | |||
| d) ang (er eIndZ | |||
| m) angel aNg@L | |||
| r) ang (e eIndZ | |||
| r) anging eIndZIN | |||
| r) anged (S1 d | |||
| @@ -782,7 +785,7 @@ | |||
| app (licab a2p | |||
| app (reh ap | |||
| apres apreI | |||
| _) apprec (i a2pri:S | |||
| _) apprec (L02 a2pri:S | |||
| _) ap (ri eIp | |||
| ap (ro eIp | |||
| _) ap (s ap | |||
| @@ -1297,7 +1300,6 @@ | |||
| e) ch (el S | |||
| cli) ch S | |||
| fi) ch S | |||
| li) ch k | |||
| ni) ch S | |||
| clo) ch S | |||
| _o) ch (e S | |||
| @@ -1464,6 +1466,7 @@ | |||
| d (d | |||
| _) d' (AP2 d | |||
| @@e) d (_S1 d // suffix | |||
| db (_ d,i:bi: | |||
| ddh d | |||
| dj dZ | |||
| dg (_ dZ | |||
| @@ -1729,7 +1732,7 @@ | |||
| fr) e (q i: | |||
| _s) e (que i: | |||
| e (quip %I | |||
| e (quiv %I | |||
| equiv %IkwIv | |||
| e'er e@ | |||
| h) e (sion 'i: | |||
| &f) e's (_S2i s | |||
| @@ -2038,6 +2041,7 @@ | |||
| engin EndZIn | |||
| eng (_ 'EN // place names | |||
| enging EndZIN | |||
| eng (th EN | |||
| en (ig En | |||
| en (igma_ %En | |||
| &) enine @ni:n | |||
| @@ -2251,7 +2255,7 @@ | |||
| z) er (o i@r | |||
| _C) er (o_ i@r | |||
| er (rA E | |||
| err (_ 3: | |||
| err (_N e@ | |||
| .group es | |||
| &) es (_S1i z | |||
| @@ -2477,7 +2481,7 @@ | |||
| gue (_ g | |||
| _) gue gE | |||
| _) guer (n g3: | |||
| ar) gue gju: | |||
| // _ar) gu gju: | |||
| .group h | |||
| h h | |||
| @@ -2606,6 +2610,7 @@ | |||
| if (icAnC 'If | |||
| r) i (fl aI | |||
| st) i (fl aI | |||
| i (genous 'I | |||
| igeo IdZ@ | |||
| n) ihi aI|@ | |||
| @@ -2648,34 +2653,8 @@ | |||
| sh) i (ma_ 'i: | |||
| i (mum I | |||
| @) i (ness I | |||
| io (_ =I2oU | |||
| ?7 io (_ =i:oU | |||
| b) io aIoU | |||
| b) io (logy aI0 | |||
| v) io aI0 | |||
| i (o I2 | |||
| ?7 i (o i: | |||
| io (li_ I2'oU | |||
| &) ion (_ =i@n | |||
| ?8 &) ion (_ =IVn | |||
| n) ion =i@n | |||
| v) io (l aI@ | |||
| g) io (n @ | |||
| m) io (n I20 | |||
| sh) io (n @ | |||
| _) io (n aI0 | |||
| _l) ion aI@n | |||
| z) io (n aI@ | |||
| r) ior (_ I3 | |||
| &) ior (+ i@3 | |||
| &) ior (_ j3 | |||
| iority I'0rI2t%I | |||
| iou (rA j@ | |||
| iour (K j3 | |||
| @) ious (_ =I2@s | |||
| ioux u: | |||
| _r) io (t aI@ | |||
| io (t_ I|@ | |||
| ipede Ipi:d | |||
| _s) i (ph aI | |||
| i (que_ 'i: | |||
| @@ -2697,6 +2676,7 @@ | |||
| iz (er_ aIz | |||
| prAm) is Is | |||
| @Cs) is (_ =Is | |||
| b) is (_ Is | |||
| ize (_ aIz | |||
| ise (d_ aIz | |||
| ize (d_ aIz | |||
| @@ -2899,21 +2879,21 @@ | |||
| ?3 s) im (ult aIm | |||
| .group in | |||
| @) ing (_+S3dve I2N | |||
| @) ings (_S4dve I2Nz | |||
| @) ingly (_S5dve I2Ng-lI | |||
| @) ingment (_S7dve I2Ng-m@nt | |||
| logu) ing (_S4v I2N | |||
| x) ing (_+S3v I2N | |||
| el) ing (_+S3dv I2N | |||
| @@om) ing (_S3dv I2N | |||
| en) ing (_S3v I2N | |||
| en) ings (_S4v I2Nz | |||
| en) ingly (_S5vf I2Ng-lI | |||
| er) ing (_S3v I2N | |||
| er) ings (_S4v I2Nz | |||
| er) ingly (_S5vf I2Ng-lI | |||
| er) ingment (_S7v I2Ng-m@nt | |||
| @) ing (_+S3dve IN | |||
| @) ings (_S4dve INz | |||
| @) ingly (_S5dve INg-lI | |||
| @) ingment (_S7dve INg-m@nt | |||
| logu) ing (_S4v IN | |||
| x) ing (_+S3v IN | |||
| el) ing (_+S3dv IN | |||
| @@om) ing (_S3dv IN | |||
| en) ing (_S3v IN | |||
| en) ings (_S4v INz | |||
| en) ingly (_S5vf INg-lI | |||
| er) ing (_S3v IN | |||
| er) ings (_S4v INz | |||
| er) ingly (_S5vf INg-lI | |||
| er) ingment (_S7v INg-m@nt | |||
| Br) ing (_ IN | |||
| ?7 &) in (_ @n | |||
| @@ -3081,6 +3061,34 @@ | |||
| _) intra Intr@ | |||
| _) intra (CC %Intra | |||
| .group io | |||
| io (_ =I2oU | |||
| ?7 io (_ =i:oU | |||
| b) io aIoU | |||
| b) io (logy aI0 | |||
| v) io aI0 | |||
| io (li_ I2'oU | |||
| &) ion (_ =i@n | |||
| ?8 &) ion (_ =IVn | |||
| n) ion =i@n | |||
| v) io (l aI@ | |||
| g) io (n @ | |||
| m) io (n I20 | |||
| sh) io (n @ | |||
| _) io (n aI0 | |||
| _l) ion aI@n | |||
| z) io (n aI@ | |||
| r) ior (_ I3 | |||
| &) ior (+ i@3 | |||
| &) ior (_ j3 | |||
| iority I'0rI2t%I | |||
| iou (rA j@ | |||
| iour (K j3 | |||
| @) ious (_ =I2@s | |||
| ioux u: | |||
| _r) io (t aI@ | |||
| io (t_ I|@ | |||
| .group ir | |||
| _) ir (a I2r | |||
| ir (a_ 'i@r | |||
| @@ -3339,6 +3347,8 @@ | |||
| @) men (_ mEn | |||
| &) ment (_S4 m@nt | |||
| &) ments (_S5 m@nt|s | |||
| u) ment (_ m@nt | |||
| u) ments (_ m@nt|s | |||
| ?8 &) ment (_S4 mEnt | |||
| ?8 &) ments (_S5 mEnt|s | |||
| mEnt (_ m@nt | |||
| @@ -3395,7 +3405,7 @@ | |||
| n) n | |||
| &ia) n (_S1 n | |||
| &ia) ns (_S2 nz | |||
| @) name (_ neIm | |||
| @) name (_S4 neIm | |||
| _) nano (P4 n,anoU | |||
| nause nO:sI | |||
| necessit n@sEsIt | |||
| @@ -3566,7 +3576,8 @@ | |||
| o (ffic 0 | |||
| o (gan_ oU | |||
| &) o (gen_ @ | |||
| hom) o (gen '0 | |||
| o (genous '0 | |||
| o (geny '0 | |||
| ogeni (c oUdZ'EnI | |||
| r) o (ger 0 | |||
| l) o (gy @ | |||
| @@ -3574,7 +3585,7 @@ | |||
| r) ogue oUg | |||
| v) ogue oUg | |||
| @@) ogue 0g | |||
| @) oged 0gd | |||
| @l) oge (_ 0g | |||
| oh oU | |||
| o (hA oU | |||
| j) oh (n 0 | |||
| @@ -3653,11 +3664,6 @@ | |||
| tr) othe oUD | |||
| l) oth (ian oUD | |||
| _r) o (ther 0 | |||
| ph) oto oUtoU | |||
| ph) o (ton oU | |||
| ph) otocop oUt@k0p | |||
| ph) oto (grapher @t0 | |||
| ph) oto (graphy @t0 | |||
| pr) oto oUtoU | |||
| pr) oto (n oUt0 | |||
| m) otor oUt@ | |||
| @@ -3715,7 +3721,7 @@ | |||
| olo (gic @l'0 | |||
| v) olt oUlt | |||
| w) olv Ulv | |||
| _p) oly ,0lI | |||
| N_p) oly ,0lI | |||
| .group om | |||
| &) om (_ @m | |||
| @@ -3910,7 +3916,7 @@ | |||
| _) or (iC 0r | |||
| @t) ore (_ 3 | |||
| st) ore (_ o@ | |||
| @) orily (_ '0r@l%I | |||
| @) orily (_ =@r@l%I | |||
| h) ori (z @raI | |||
| h) ori (zont 0rI | |||
| ?!3 _h) or (o 0r | |||
| @@ -4206,6 +4212,14 @@ | |||
| p (haza p | |||
| ph (erd p | |||
| phila fIla | |||
| _) photo (@@P5 f,oUtoU | |||
| photo foUtoU | |||
| photon foUt0n | |||
| photocop foUt@k0p | |||
| photo (grapher f@t0 | |||
| photo (graphy f@t0 | |||
| photo (met foUt'0 | |||
| _) phyco f,aIkoU | |||
| p (hole p | |||
| sym) pa p@ | |||
| _) paleo (@P5 p,eIli:oU | |||
| @@ -4289,7 +4303,7 @@ | |||
| _) pre (ss prE | |||
| _) pre (st prE | |||
| _) pre (u pr%i: | |||
| _) pre (val prE | |||
| _) prev (al prEv | |||
| _) pre (vio pri: | |||
| _) pre (view pri: | |||
| _) pri (o praI | |||
| @@ -4445,6 +4459,7 @@ | |||
| _) re (i@P2 r,i: | |||
| _) rei (c raI | |||
| _) rei (l raI | |||
| rei (s raI | |||
| _) rele (g rElI2 | |||
| rele (nt rI2lE | |||
| rele (v rElI | |||
| @@ -4497,7 +4512,7 @@ | |||
| s (s | |||
| s (sh s | |||
| _) sch S | |||
| sch (em sk | |||
| sche (m ski: | |||
| _) sch (ism sk | |||
| _) schiz skIts | |||
| sch (o sk | |||
| @@ -4750,6 +4765,7 @@ | |||
| ca) th (eri T | |||
| _e) th (er T | |||
| th (ern_ D | |||
| _) thio T,aIoU | |||
| th (ith D | |||
| th (ole th | |||
| _) th (om@ t | |||
| @@ -4767,16 +4783,17 @@ | |||
| .group u | |||
| u V | |||
| u (_N u: | |||
| u (_ ju: | |||
| r) u (_ u: | |||
| l) u (_ u: | |||
| w) u (_ u: | |||
| L01) u (_ u: | |||
| h) u (_ =u: | |||
| men) u (_ ju: | |||
| u (ga_ 'u: | |||
| u (ki_ 'u: | |||
| u (ma_ 'u: | |||
| u (mo_ 'u: | |||
| u (CA ju: | |||
| u (Cu_ u: | |||
| ?3 d) u (CA u: | |||
| ?3 n) u (CA u: | |||
| ?3 t) u (CA+ u: | |||
| @@ -4954,24 +4971,20 @@ | |||
| _) una (b ,Vna2 | |||
| t) un (e ju:n | |||
| ?3 t) un (e u:n | |||
| _) un (if ju:n | |||
| un (ani %ju:n | |||
| _) under (@P5 ,Vnd3 // prefix | |||
| _) un (deP2 ,Vn | |||
| _) un (dula Vn | |||
| _) un (enP2 ,Vn | |||
| _) un (exP2 ,Vn | |||
| _) un (ic ju:n | |||
| _) un (imP2 ,Vn | |||
| _) unin ,VnI2n | |||
| un (inj %Vn | |||
| _) uni ju:nI | |||
| _) un (id ,Vn | |||
| _) un (inP2 ,Vn | |||
| _) un (il ,ju:n | |||
| _) un (io ju:n | |||
| _) un (iq %ju:n | |||
| _) un (is ju:n | |||
| _) un (it ju:n | |||
| unit (e ju:n'aIt | |||
| _) un (iv ju:n | |||
| _) un (ix ju:n | |||
| un (i ju:n | |||
| p) un (ish Vn | |||
| @@ -5050,6 +5063,8 @@ | |||
| .group v | |||
| v v | |||
| v (v | |||
| @) va (len veI | |||
| _) vehem vi@m | |||
| _) vi (brat v%aI | |||
| vivi (@ vIvI | |||
| @@ -5076,6 +5091,7 @@ | |||
| wh (ol h | |||
| m) w (ich_ | |||
| B) wing (_ wIN | |||
| B) wing (s_ wIN | |||
| @) wise (_S4 waIz | |||
| e) with (_ w'ID | |||
| with (C w%ID | |||
| @@ -5096,7 +5112,7 @@ | |||
| _) x z | |||
| xio (n kS@ | |||
| xious =kS@s | |||
| xu (a kSu: | |||
| xu (a =kSu: | |||
| .group y | |||
| y j | |||
| @@ -5146,7 +5162,7 @@ | |||
| d) ynam aInam | |||
| @C) y (mAn_ I | |||
| w) y (n I | |||
| gl) y (ce I | |||
| gl) y (cer I | |||
| d) yse (n Is@ | |||
| f) y (_ aI | |||
| ff) y (_ I | |||
| @@ -5251,6 +5267,7 @@ | |||
| Em (_ @m | |||
| @) E (mber 'E | |||
| Eme (_ i:m | |||
| Em (ic_ 'i:m | |||
| Ensk (_ 'Ensk | |||
| En (_ @n | |||
| ?8 En (_ En | |||
| @@ -5298,6 +5315,7 @@ | |||
| Esque 'Esk | |||
| E (ss E | |||
| Ess (_ Es | |||
| E (te_ i: | |||
| E (tric E | |||
| Etta (_ 'Et@ | |||
| Ette (_ 'Et | |||
+ 3
- 3
dictsource/fr_rules
View File
| @@ -23,7 +23,7 @@ | |||
| // 2006-11-18 Gilles Casse <[email protected]> | |||
| // | |||
| // Updated: 2009-10-15 Michel Such <[email protected]> | |||
| // Updated: 2009-11-20 Michel Such <[email protected]> | |||
| // | |||
| // Letter classes: | |||
| @@ -753,6 +753,7 @@ C) i (es_ i | |||
| dist) ill il // distiller | |||
| _L05) ill il // Lille, mille, ville, william | |||
| osc) ill il // osciller | |||
| gu) ill ij // guillaume | |||
| qu) ill ij // quille | |||
| A) ill j // caillou | |||
| C) ill ij // famille | |||
| @@ -1363,7 +1364,7 @@ VCi) t (_ t2 | |||
| .group v | |||
| v v | |||
| vers (_ vErz2 | |||
| Xri) ver (X vWr | |||
| dri) ver (X vWr | |||
| _) view (X vju | |||
| _) view (A vjuv | |||
| @@ -1477,4 +1478,3 @@ _r) w (an u // Rwanda | |||
+ 1
- 1
dictsource/hi_rules
View File
| @@ -2,7 +2,7 @@ | |||
| // This file is UTF8 encoded | |||
| // letter groups: | |||
| // A vowel letters | |||
| // A vowel letters and vowel signs | |||
| // B vowel signs and virama ् | |||
| // C consonants | |||
| // Y vowel letters and vowel signs | |||
+ 290
- 43
dictsource/hu_list
View File
| @@ -25,12 +25,11 @@ _7X hEtvEn | |||
| _8X n^oltsvAn | |||
| _9X kilEntsvEn | |||
| _0C sa:z | |||
| _0M1 EzER2 | |||
| _1M1 EzER2 | |||
| _2M1 ke:tEzER2 | |||
| _0M2 millio: | |||
| _1M2 millio: | |||
| _1M2 EJmillio: | |||
| _2M2 ke:tmillio: | |||
| _0M3 millia:R2d | |||
| _1M3 EJmillia:R2d | |||
| @@ -95,7 +94,16 @@ _0-ei Ei $alt2 | |||
| _0-től e:tY:l $alt2 | |||
| _0-tól a:to:l $alt2 | |||
| _0-ig e:ig $alt2 //special date ordinal numbers for example elsejéig, negyedikéig etc. | |||
| _0-éről e:R2Y:l $alt2 | |||
| _0-áról a:R2o:l $alt2 | |||
| _0-ára a:R2A $alt2 | |||
| _0-ától a:to:l $alt2 | |||
| _0-ről e:R2Y:l $alt2 | |||
| _0-ról a:R2o:l $alt2 | |||
| _0-ével e:vEl $alt2 | |||
| _0-ával a:vAl $alt2 | |||
| _0-éig e:ig $alt2 | |||
| _0-áig a:ig $alt2 | |||
| (1-e) elseje $text $alt2 | |||
| (1-én) elsején $text $alt2 | |||
| (1-jén) elsején $text $alt2 | |||
| @@ -105,7 +113,10 @@ _0-ig e:ig $alt2 //special date ordinal numbers for example elsejéig, negyedik | |||
| (1-re) elsejére $text $alt2 | |||
| (1-től) elsejétől $text $alt2 | |||
| (1-ig) elsejéig $text $alt2 | |||
| (1-éről) elsejéről $text $alt2 | |||
| (1-ről) elsejéről $text $alt2 | |||
| (1-ével) elsejével $text $alt2 | |||
| (1-éig) elsejéig $text $alt2 | |||
| (2-i) másodikai $text $alt2 | |||
| (2-ig) másodikáig $text $alt2 | |||
| (3-i) hAR2_mAdikAi $alt2 | |||
| @@ -118,7 +129,6 @@ _0-ig e:ig $alt2 //special date ordinal numbers for example elsejéig, negyedik | |||
| (16-ig) tizenhatodikáig $text $alt2 | |||
| (18-ig) tizennyolcadikáig $text $alt2 | |||
| (20-i) huszadikai $text $alt2 | |||
| (20-ig) huszadikáig $text $alt2 | |||
| (23-ig) huszonharmadikáig $text $alt2 | |||
| (26-ig) huszonhatodikáig $text $alt2 | |||
| @@ -128,10 +138,14 @@ _0-ig e:ig $alt2 //special date ordinal numbers for example elsejéig, negyedik | |||
| // these exceptions only for 0, not for other numbers ending in '0' | |||
| (0-ás) nul:a:S | |||
| (0-t) nul:a:t | |||
| (0-val) nul:a:vAl | |||
| (0-ra) nul:a:R2A | |||
| (0-nál) nul:a:na:l | |||
| (0-hoz) nul:a:hoz | |||
| // entries with a single digit such as (2-i) also apply to 22, 32, etc, unless $only | |||
| @@ -159,22 +173,29 @@ _0-ig e:ig $alt2 //special date ordinal numbers for example elsejéig, negyedik | |||
| (2-esekkel) kEt:ESEk:El | |||
| (2-eseket) kEt:ESEkEt | |||
| (2-eseik) kEt:ESEik | |||
| (2-esük) kEt:ESyk | |||
| (3-as) ha:R2mAS | |||
| (3-asának) ha:R2mASa:nAk | |||
| (3-ason) ha:R2mASon | |||
| (3-assal) ha:R2mAS:Al | |||
| (3-asával) ha:R2mASa:vAl | |||
| (3-ast) ha:R2mASt | |||
| (3-astól) ha:R2mASto:l | |||
| (3-ashoz) ha:R2mAShoz | |||
| (3-at) ha:R2mAt | |||
| (3-al) ha:R2om:Al | |||
| (4-el) ne:J:El //4 number suffixes (now contains one suffix) | |||
| //4 number suffixes | |||
| (4-el) ne:J:El //Nneed J: phoneme, not J phoneme contains one suffix) | |||
| (4-gyel) ne:J:El //Need J: phoneme, not J phoneme | |||
| (5-tel) Yt:El | |||
| (5-el) Yt:El | |||
| (5-től) Yt:Y:l | |||
| (5-től) YtYdike:tY:l $alt2 | |||
| (6-al) hAt:Al | |||
| (6-tal) hAt:Al | |||
| (6-tól) hAt:o:l | |||
| (6-tól) h'Atodika:to:l $alt2 | |||
| (7-es) hEtES | |||
| (7-est) hEtESt | |||
| (7-esek) hEtESEk | |||
| @@ -185,16 +206,23 @@ _0-ig e:ig $alt2 //special date ordinal numbers for example elsejéig, negyedik | |||
| (7-esük) hEtESyk | |||
| (7-tel) he:t:El | |||
| (7-el) he:t:El | |||
| (7-től) he:t:Y:l | |||
| (7-től) hEtEdike:tY:l $alt2 | |||
| (7-essel) hEtES:El | |||
| (10-es) tizES // use [i] not [i:] | |||
| (10-est) tizESt | |||
| (10-essel) tizES:El | |||
| (10-esével) tizESe:vEl | |||
| (10-en) tizEn | |||
| (10-et) tizEt | |||
| (10-szer) ti:s:ER2 | |||
| (10-szeres) ti:s:ER2ES | |||
| (20-as) husAS // use [u] not [u:] | |||
| (20-ast) husASt | |||
| (20-assal) husAS:Al | |||
| (20-asával) husASa:vAl | |||
| (20-at) husAt | |||
| //special number exceptions | |||
| (10-el) ti:zzEl | |||
| @@ -234,7 +262,7 @@ júl $alt | |||
| aug $alt | |||
| szept $alt | |||
| okt $alt | |||
| now $alt | |||
| nov $alt | |||
| dec $alt | |||
| //this following 7 lines means the 7 hungarian day name | |||
| @@ -268,14 +296,19 @@ _#9 tAb | |||
| _#13 vAlAmi | |||
| _#32 so:kYz | |||
| _cap n'AJ_| | |||
| _?? kAR2AktEr||ko:d // unknown characters (change this) | |||
| // Abbreviations | |||
| ADSL a:de:ESEl $allcaps //Internet connection type, we pronouns this with ádéesel | |||
| ÁNTSZ a:Ente:Es $allcaps | |||
| ATM a:te:Em $allcaps //The ATM stands. We pronouns this abbreviation with átéem word. Default, Espeak pronouns this abbreviation with atéem word. | |||
| km kilo:me:tER2 | |||
| GYSEV JESEv $allcaps | |||
| GYESEV JESEv $allcaps | |||
| HÉV he:v $allcaps | |||
| City siti $capital | |||
| IPTV $abbrev $allcaps | |||
| GDP dZi:di:pi: $allcaps | |||
| HSDPA $abbrev $allcaps | |||
| ORTT $abbrev $allcaps | |||
| @@ -283,27 +316,29 @@ ORFK oEREfka: $abbrev $allcaps | |||
| MÁV ma:v $allcaps | |||
| MTI $abbrev $allcaps | |||
| mm milime:tER2 | |||
| RAM R2Am $allcaps //Espeak normaly spokening this abbreviation with erraem, but this is not good | |||
| Psszt ps:t $capital // similar word with quiet word. Espeak default spokening this abbrew quiet word with letter by letter by default. | |||
| VDSZSZ ve:de:EsEs $allcaps | |||
| a.m An^n^i||m'int $dot | |||
| ún u:JnEvEzEt: $dot | |||
| ún u:JnEvEzEt: $hasdot | |||
| dr doktoR2 $dot | |||
| mr mistER2 $dot //in hungarian we not use, but lot of books contains this word. | |||
| mrs misis $dot //In hungarian we not use, but lot of book contains this word. | |||
| mr mistER2 $hasdot //in hungarian we not use, but lot of books contains this word. | |||
| mrs misis $hasdot //In hungarian we not use, but lot of book contains this word. | |||
| miss mis: $hasdot | |||
| gpu $abbrev | |||
| GB gigAba:jt $allcaps | |||
| MB mEgAba:jt $allcaps | |||
| OK ok $allcaps | |||
| mvgyosz Emve:Je:oEs | |||
| OTP o:te:pe: $allcaps | |||
| id idY:SEb: $dot | |||
| ill illEtvE $dot | |||
| ifj ifjAb: $dot | |||
| id idY:SEb: $hasdot | |||
| ill illEtvE $hasdot | |||
| ifj ifjAb: $hasdot | |||
| mta $abbrev | |||
| pl pe:lda:ul $dot | |||
| stb SAtYb:i $dot | |||
| u.n u:JnEvEzEt: $dot | |||
| ú.n u:JnEvEzEt: $dot | |||
| pl pe:lda:ul $hasdot | |||
| stb SAtYb:i $hasdot | |||
| u.n u:JnEvEzEt: $hasdot | |||
| ú.n u:JnEvEzEt: $hasdot | |||
| vö v'EZd||_'Yss2E | |||
| @@ -336,7 +371,7 @@ maguk $unstressend | |||
| de $u+ $pause // but | |||
| vagy $u+ $pause // or | |||
| mert $u $pause // because | |||
| mert $u $pause // because | |||
| miatt $u // because | |||
| bár $u $pause // although | |||
| habár $u $pause // although | |||
| @@ -348,7 +383,8 @@ noha $u $pause // even thought | |||
| // Negative | |||
| nem $unstressend $combine $strend | |||
| nem $strend2 $combine | |||
| ?2 nem $strend2 | |||
| ne $unstressend | |||
| e $u // "-e" question | |||
| @@ -380,9 +416,9 @@ fölé $unstressend | |||
| felett $unstressend // above | |||
| fölött $unstressend | |||
| //mellől $u // besides | |||
| //mellé $u | |||
| //mellett $u | |||
| mellől $unstressend // besides | |||
| mellé $unstressend | |||
| mellett $unstressend | |||
| lett $unstressend | |||
| ott $unstressend | |||
| itt $unstressend | |||
| @@ -391,9 +427,9 @@ nektek $unstressend | |||
| nekik $unstressend | |||
| neki $unstressend | |||
| nekem $unstressend | |||
| //közül $u | |||
| //közé $u | |||
| //között $u | |||
| közül $unstressend | |||
| közé $unstressend | |||
| között $u | |||
| an $u // so many persons | |||
| as $u | |||
| ba $unstressend // into | |||
| @@ -426,6 +462,7 @@ ről $unstressend | |||
| szer $u | |||
| szor $u // times | |||
| szó $unstressend | |||
| szót $unstressend | |||
| szór $u | |||
| ször $u | |||
| tól $unstressend // from | |||
| @@ -465,8 +502,8 @@ rá $unstressend //onto | |||
| ide $unstressend // here | |||
| oda $unstressend // there | |||
| szét $unstressend //apart | |||
| //össze $u //connect with | |||
| //vissza $u //back | |||
| össze $unstressend //connect with | |||
| vissza $unstressend //back | |||
| volna $unstressend // would | |||
| //részén $u //on ... part of | |||
| @@ -488,6 +525,7 @@ jót $unstressend | |||
| kér $unstressend | |||
| tartják $unstressend | |||
| erős $unstressend | |||
| lenni $unstressend | |||
| lennie $unstressend | |||
| közt $u+ | |||
| levegőjére $unstressend | |||
| @@ -505,6 +543,7 @@ lenne $unstressend | |||
| őt $unstressend | |||
| helyes $u+ | |||
| fák $unstressend | |||
| fát $unstressend | |||
| et $unstressend | |||
| megvédeni $unstressend | |||
| sztrájk $unstressend | |||
| @@ -552,6 +591,7 @@ srác $unstressend | |||
| rám $unstressend | |||
| tűnik $unstressend | |||
| nyújt $unstressend | |||
| nincs $unstressend | |||
| nincsen $unstressend | |||
| mégy $unstressend | |||
| nő $unstressend | |||
| @@ -565,7 +605,8 @@ düh $unstressend | |||
| más $unstressend | |||
| mást $unstressend | |||
| rúd $unstressend | |||
| mint $unstressend $brk $combine | |||
| mint $unstressend $combine | |||
| ?2 mint $unstressend | |||
| iránt $unstressend | |||
| légy $unstressend | |||
| tűnt $unstressend | |||
| @@ -586,6 +627,7 @@ jött $unstressend | |||
| szólsz $unstressend | |||
| lőtt $unstressend | |||
| sor $unstressend | |||
| sort $unstressend | |||
| árt $unstressend | |||
| fest $unstressend | |||
| fújt $unstressend | |||
| @@ -622,7 +664,167 @@ napját $unstressend | |||
| több $unstressend | |||
| tart $unstressend | |||
| hág $unstressend | |||
| sors $unstressend | |||
| küzd $unstressend | |||
| vert $unstressend | |||
| csaj $unstressend | |||
| tárgy $unstressend | |||
| lágy $unstressend | |||
| pont $unstressend //This is mean pont word, not dot character. | |||
| pontok $unstressend | |||
| bújt $unstressend | |||
| mély $unstressend | |||
| úr $unstressend | |||
| szép $unstressend | |||
| szék $unstressend | |||
| nagy $unstressend | |||
| kár $unstressend | |||
| hó $unstressend | |||
| tánc $unstressend | |||
| füst $unstressend | |||
| két $unstressend | |||
| őr $unstressend | |||
| őrt $unstressend | |||
| nyílt $unstressend | |||
| fényt $unstressend | |||
| éjt $unstressend | |||
| ég $unstressend | |||
| lépett $unstressend | |||
| perc $unstressend | |||
| halk $unstressend | |||
| busz $unstressend | |||
| gyors $unstressend | |||
| vett $unstressend | |||
| kést $unstressend | |||
| fess $unstressend | |||
| szín $unstressend | |||
| szög $unstressend | |||
| sincs $unstressend | |||
| tér $unstressend | |||
| sztár $unstressend | |||
| vers $unstressend | |||
| mondja $unstressend | |||
| mondják $unstressend | |||
| mondta $unstressend | |||
| mondták $unstressend | |||
| szert $unstressend | |||
| látja $unstressend | |||
| szél $unstressend | |||
| óra $unstressend | |||
| hegy $unstressend | |||
| colt $unstressend | |||
| róla $unstressend | |||
| rólunk $unstressend | |||
| rólatok $unstressend | |||
| róluk $unstressend | |||
| szád $unstressend | |||
| nos $u | |||
| no $u | |||
| na $u | |||
| vall $unstressend | |||
| magam $unstressend | |||
| magad $unstressend | |||
| tűz $unstressend | |||
| egy $unstressend | |||
| lehetett $unstressend | |||
| arra $unstressend | |||
| erre $unstressend | |||
| arról $unstressend | |||
| erről $unstressend | |||
| ölt $unstressend | |||
| rosszak $unstressend | |||
| helyt $unstressend | |||
| bort $unstressend | |||
| látszik $unstressend | |||
| látszott $unstressend | |||
| látszanak $unstressend | |||
| látszotok $unstressend | |||
| körül $unstressend | |||
| dőlt $unstressend | |||
| vér $unstressend | |||
| sót $unstressend | |||
| múlt $unstressend | |||
| ügy $unstressend | |||
| cél $unstressend | |||
| célt $unstressend | |||
| láb $unstressend | |||
| bőr $unstressend | |||
| víz $unstressend | |||
| fagy $unstressend | |||
| nyelt $unstressend | |||
| sokk $unstressend | |||
| hét $unstressend | |||
| zajt $unstressend | |||
| pest $unstressend | |||
| stáb $unstressend | |||
| súlyt $unstressend | |||
| szólt $unstressend | |||
| vidd $unstressend | |||
| fönn $unstressend | |||
| szűk $unstressend | |||
| fordul $unstressend | |||
| fordult $unstressend | |||
| hús $unstressend | |||
| bor $unstressend | |||
| húsz $unstressend | |||
| tőle $unstressend | |||
| tőled $unstressend | |||
| tőlük $unstressend | |||
| tőletek $unstressend | |||
| tőlünk $unstressend | |||
| mászni $unstressend | |||
| jel $unstressend | |||
| szállt $unstressend | |||
| száll $unstressend | |||
| sínt $unstressend | |||
| kút $unstressend | |||
| bőrt $unstressend | |||
| vért $unstressend | |||
| lóg $unstressend | |||
| vette $unstressend | |||
| lenn $unstressend | |||
| indult $unstressend | |||
| völgy $unstressend | |||
| frászt $unstressend | |||
| hang $unstressend | |||
| fény $unstressend | |||
| kösz $unstressend | |||
| gramm $unstressend | |||
| húst $unstressend | |||
| telt $unstressend | |||
| zár $unstressend | |||
| rész $unstressend | |||
| nyom $unstressend | |||
| hiszem $unstressend | |||
| hiszed $unstressend | |||
| hiszi $unstressend | |||
| telik $unstressend | |||
| adott $unstressend | |||
| gázt $unstressend | |||
| csap $unstressend | |||
| falán $unstressend | |||
| hitte $unstressend | |||
| nyár $unstressend | |||
| túl $unstressend | |||
| fáj $unstressend | |||
| tudni $unstressend | |||
| hinni $unstressend | |||
| hopp $unstressend | |||
| vinni $unstressend | |||
| hozni $unstressend | |||
| hittem $unstressend | |||
| hitted $unstressend | |||
| hittük $unstressend | |||
| hittétek $unstressend | |||
| hitték $unstressend | |||
| folt $unstressend | |||
| írva $unstressend | |||
| vele $unstressend | |||
| veled $unstressend | |||
| velem $unstressend | |||
| velünk $unstressend | |||
| veletek $unstressend | |||
| velük $unstressend | |||
| // word pairs | |||
| @@ -635,10 +837,10 @@ hág $unstressend | |||
| vagyok $u // to be, present | |||
| vagy $u | |||
| van $u | |||
| vagyunk $u | |||
| vagytok $u | |||
| vannak $u | |||
| van $unstressend | |||
| vagyunk $unstressend | |||
| vagytok $unstressend | |||
| vannak $unstressend | |||
| voltam $u // to be, past | |||
| voltál $u | |||
| @@ -666,7 +868,7 @@ fogunk $u+ | |||
| fogtok $u+ | |||
| fognak $u+ | |||
| tud $u+ // can | |||
| tud $unstressend // can | |||
| tudok $u+ | |||
| tudsz $u+ | |||
| tudunk $u+ | |||
| @@ -751,7 +953,7 @@ _? ke:R2dY:jEl | |||
| _- m'inus $max3 | |||
| __ Ala:hu:za:S $max3 | |||
| _' ApostR2o:f | |||
| _– nAJkYtY: | |||
| _– gondolAtjEl | |||
| _— kviR2tmi:nus | |||
| _" ide:zY:jEl | |||
| _( b'Alza:R2o:jEl $max3 | |||
| @@ -762,17 +964,56 @@ _{ k'EzdY:kAptSoS $max3 | |||
| _} v'e:gkAptSoS $max3 | |||
| _… pontpontpont | |||
| _• di:spont | |||
| _• fElSoR2ola:SjEl | |||
| _| fyg:Y:lEgESvonAl | |||
| _> nAJob | |||
| _< kiSSEb | |||
| _¤ pe:nznEmjEl | |||
| ® bEjEJzEt: | |||
| ™ ve:djEJ | |||
| _` tompA | |||
| _ SokYz | |||
| _« bElSY:|bAl|ide:zY:jEl | |||
| _» bElSY:|jobb|ide:zY:jEl | |||
| _ la:JkYtY:jEl | |||
| _² ma:Sodik|hAtva:n^ | |||
| _³ hArmAdik|hAtva:n^ | |||
| _· kYze:pSY:pont | |||
| _¹ ElsY:hAtva:n^ | |||
| _º Sorsa:m | |||
| _‘ bAloldAli|ide:zY:jEl | |||
| _’ job:oldAli|ide:zY:jEl | |||
| _‚ ide:zY:jEl | |||
| _‛ ide:zY:jEl | |||
| _“ ide:zY:jEl | |||
| _” ide:zY:jEl | |||
| _„ ide:zY:jEl | |||
| _‟ ide:zY:jEl | |||
| _‣ ha:R2omsYgAlAku:|fElSoR2ola:SjEl | |||
| _‰ EzR2Ele:k | |||
| _′ ApostR2o:f | |||
| _″ duplA|ApostR2o:f | |||
| © tsopiR2ight-jEl | |||
| ° fok | |||
| − minus | |||
| ± plusminus | |||
| µ my: | |||
| ¼ nEJEd | |||
| ½ fe:l | |||
| ¾ ha:R2omnEJEd | |||
| × tAlpAS | |||
| ÷ osta:S | |||
| ¬ logikAinEm | |||
| √ JYkjEl | |||
| ∞ vEgtElEn | |||
| ≠ nEmEJEnlY: | |||
| _ˇ lEfEle:n^i:l | |||
| // Main Exceptions List | |||
| //===================== | |||
| nato na:to: | |||
| (end-of line) u:jS,oR2 | |||
| $textmode | |||
| MSZP emeszpé | |||
| @@ -792,3 +1033,9 @@ egyezség eggyesség | |||
| (db-os) darabos | |||
| (db-ot) darabot | |||
+ 523
- 154
dictsource/hu_rules
File diff suppressed because it is too large
View File
+ 52
- 5
dictsource/no_list
View File
| @@ -72,24 +72,51 @@ _1M2 'e:n||m'Illi:;,u:n | |||
| _0and u:g | |||
| _dpt kOmmA | |||
| // ordinal numbers | |||
| _ord @nd@2 | |||
| _1o f'WRst@2 | |||
| _2o 'AndR@2 | |||
| _3o tR'Edj@2 | |||
| _4o fj'a:R@2 | |||
| _5o f'Emt@2 | |||
| _6o S'Et:@2 | |||
| _8o 'Ot:@nd@2 | |||
| _11o 'EllEvt@2 | |||
| _12o t'Olvt@2 | |||
| _13o tR'Et:@nd@2 | |||
| _14o fj'URt@md@2 | |||
| _15o f'Emt@nd@2 | |||
| _16o s'Ekst@nd@2 | |||
| _17o s'yt:@nd@2 | |||
| _18o 'At:@nd@2 | |||
| _19o n'It:@nd@2 | |||
| _2Xo s;'u-:@nd@2 | |||
| _0Co h'u-ndR@d@2 | |||
| _0M1o t'u-:s@nd@2 | |||
| // punctuation and symbols | |||
| //======================== | |||
| * ss;aRn@2 $max3 | |||
| = aRli:k $max3 | |||
| + plu-s $max3 | |||
| % pR'u:s'Ent $max3 | |||
| & O:g | |||
| # nu-mm@RtENn $max3 | |||
| / skROstR@k $max3 | |||
| \ OmvEndt||skROstR@k $max3 | |||
| _! u-:tRu:pstENn | |||
| _" AnfY:RS@l | |||
| _# nu-mm@RtENn | |||
| _$ dOllA:R | |||
| % pR'u:s'Ent | |||
| & O:g | |||
| _' ApUstR'u:f | |||
| _( paRaNt'e:s||b@j'ynn@R | |||
| _) paRaNt'e:s||Sl'u-t: | |||
| _* ss;aRn@2 | |||
| + plu-s | |||
| _, kOmmA | |||
| _- stRe:k | |||
| _. pu-Nktu-:m | |||
| / skROstR@k | |||
| _: ku:lOn | |||
| _; se:mi:ku:lOn | |||
| _< mIndR@2||En | |||
| @@ -104,7 +131,18 @@ _] h'YyR@2||h'A:ke:paRaNt'e:s | |||
| __ u-ndaRStR@k | |||
| _` 'OmvEndt||ApUstR'u:f | |||
| _#09 tA:b | |||
| _#32 mEllOmRu:m | |||
| _acu A:'ku-t: | |||
| _ced s'e:dIll@2 | |||
| _cir s'IRku-mflEks | |||
| _dia tR'e:mA | |||
| _grv gR'A:vi:s | |||
| _tld t'Ild@2 | |||
| é $accent | |||
| ü $accent | |||
| // abbreviations | |||
| @@ -250,6 +288,15 @@ _i i: | |||
| i i: $atend | |||
| // English Words | |||
| firefox _^_EN | |||
| screen _^_EN | |||
| reader _^_EN | |||
| cancel _^_EN | |||
| continue _^_EN | |||
| magnifier _^_EN | |||
| and @2nd $only | |||
| // MAIN WORD DICTIONARY | |||
| //********************* | |||
+ 1
- 11
dictsource/no_rules
View File
| @@ -29,6 +29,7 @@ | |||
| .group c | |||
| c k | |||
| cc k: | |||
| _) c (e s | |||
| c (i s | |||
| c (y s | |||
| c (ei s | |||
| @@ -207,7 +208,6 @@ | |||
| ü y: | |||
| $ dOllA:R | |||
| \\ OmvEndt||skROstR@k | |||
| ! _:'u-:tRu:pstENn_: | |||
| !) ! | |||
| @@ -218,14 +218,4 @@ | |||
| __) - (_D mi:nu-:s | |||
| A_) - (_D _ | |||
| C_) - (_D _ | |||
| --) - | |||
| * ss;aRn@2 | |||
| *) * (* | |||
| ** | |||
| **) * (_ _:: | |||
| = aRli:k | |||
| = (== | |||
| =) = (= | |||
| ==) = (_ _:: | |||
+ 121
- 0
dictsource/pap_list
View File
| @@ -0,0 +1,121 @@ | |||
| // This file is UTF8 encoded | |||
| // Spelling to phoneme words and exceptions for Papiamento | |||
| //http://papiamentu.pbworks.com/Pronouns | |||
| //http://www.papiamentu.com/vocab.html | |||
| // characters | |||
| b be | |||
| c se | |||
| d de | |||
| f Ef | |||
| g ge | |||
| h ha | |||
| j je | |||
| k ka | |||
| l El | |||
| m Em | |||
| n En | |||
| p pe | |||
| q ky | |||
| r ER | |||
| s Es | |||
| t te | |||
| v ve | |||
| w we | |||
| x Eks | |||
| z zEt | |||
| ñ en^e | |||
| _a a | |||
| _e e | |||
| _i i | |||
| _o o | |||
| _y igR'Ek $atend | |||
| // these letters are in pap_rules, but the letter names include the accent name | |||
| á $accent | |||
| é $accent | |||
| í $accent | |||
| ó $accent | |||
| ú $accent | |||
| // è $accent | |||
| // ò $accent | |||
| // ù $accrnt | |||
| // accent names | |||
| _acu skERpi | |||
| _grv gRave | |||
| // numbers | |||
| _0 z'eRo | |||
| _1 'unu | |||
| _2 d'os | |||
| _3 tR'es | |||
| _4 kwat'eR | |||
| _5 s'inku | |||
| _6 s'Ejs | |||
| _7 S'ete | |||
| _8 'otSo | |||
| _9 nw'ebe | |||
| _1X dj'es | |||
| _11 djes'un | |||
| _2X b'inti | |||
| _3X tR'inta | |||
| _4X kwaR'enta | |||
| _5X sinkw'enta | |||
| _6X ses'enta | |||
| _7X set'enta | |||
| _8X otS'enta | |||
| _9X nob'enta | |||
| _0C sj'en | |||
| _0M1 m'il | |||
| _1M1 m'il | |||
| _0M2 mi'on | |||
| _dpt _kOma/ | |||
| // common function words | |||
| un $u+ // a | |||
| algun $u+ // some | |||
| to | |||
| i $u+ $pause // and | |||
| y $u $pause // and ?? | |||
| y igR'Ek $atend | |||
| o $u+ $pause // or | |||
| òf $u+ $pause // or | |||
| ma $pause // but | |||
| ku $u+ $brk // which, that | |||
| (ken su) $u $brk | |||
| mi $u+ // I,me | |||
| bo $u+ // you | |||
| e $u+ // the. it, he, she | |||
| el $u+ // it, he, she (before 'a') | |||
| nos $u+ // we | |||
| boso $u+ // you | |||
| nan $u+ // they | |||
| ami $u+ // I | |||
| abo $u+ // you | |||
| su $u+ // his, her, its | |||
| ta $u+ // to be | |||
| tabata $u+ // was | |||
| lo $u+ // (future) | |||
| a $u+ // (past) | |||
| // tin $u+ // have | |||
| por $u+ // can | |||
| di $u+ // of | |||
| den $u+ // in | |||
| na $u+ // at | |||
+ 139
- 0
dictsource/pap_rules
View File
| @@ -0,0 +1,139 @@ | |||
| // This file is UTF8 encoded | |||
| // Spelling-to-phoneme rules for Papiamento (Curacao, Netherlands Antilles) | |||
| .group a | |||
| a a | |||
| aa a: | |||
| ai aI | |||
| .group b | |||
| b b | |||
| .group c | |||
| c k | |||
| c (Y s | |||
| ch tS | |||
| .group d | |||
| d d | |||
| dj dZ | |||
| .group e | |||
| e e | |||
| ee e: | |||
| ei eI | |||
| eu ew | |||
| .group è | |||
| è 'E | |||
| .group f | |||
| f f | |||
| .group g | |||
| g g | |||
| g (Y x | |||
| gu (Y g | |||
| .group h | |||
| h h | |||
| .group i | |||
| i i | |||
| i (A j | |||
| A) i (K j | |||
| ij eI | |||
| .group j | |||
| j j | |||
| .group k | |||
| k k | |||
| .group l | |||
| l l | |||
| .group m | |||
| m m | |||
| .group n | |||
| n n | |||
| n (_ N | |||
| &) nan (_ n%an | |||
| .group ñ | |||
| ñ n^ | |||
| .group o | |||
| o o | |||
| oe u | |||
| oo o: | |||
| ou ow | |||
| .group ò | |||
| ò 'O | |||
| .group p | |||
| p p | |||
| .group q | |||
| q k | |||
| qu (A kw | |||
| qui kwi | |||
| .group r | |||
| r R | |||
| .group s | |||
| s s | |||
| sh S | |||
| .group t | |||
| t t | |||
| .group u | |||
| u u | |||
| u (A w | |||
| ui uj | |||
| uu y | |||
| .group ù | |||
| ù Y | |||
| ùi Yj | |||
| .group ü | |||
| ü y | |||
| üi yj | |||
| .group v | |||
| v v | |||
| .group w | |||
| w w | |||
| .group x | |||
| x ks | |||
| _) x (A z | |||
| .group y | |||
| y j | |||
| K) y (K i | |||
| .group z | |||
| z z | |||
| zj Z | |||
| .group | |||
| ' ? | |||
| á ''a | |||
| é ''e | |||
| í ''i | |||
| ó ''o | |||
| ú ''u | |||
| ç s | |||
| $ dOlO | |||
+ 96
- 70
dictsource/pt_list
View File
| @@ -7,6 +7,11 @@ | |||
| // ?3 Epenthetic [I] between consonants | |||
| // ?4 Brazil mbrola voice | |||
| // $alt change [e] or [o] in the stressed syllable to [E] or [O] | |||
| // $alt2 change [E] or [O] in the stressed syllable to [e] or [o] | |||
| // Any [E] or [O] phonemes in unstressed words must be listed explicitly | |||
| // Note for "pt-pt" [R] is the same sound as [r] | |||
| // for "pt" [y] is the same sound as [i] | |||
| @@ -44,7 +49,7 @@ _à $accent | |||
| _à $accent | |||
| _â $accent | |||
| _ã $accent | |||
| _ç $accent | |||
| ç $accent | |||
| _é $accent | |||
| _ê $accent | |||
| _í $accent | |||
| @@ -205,42 +210,45 @@ vi vi | |||
| // ABBREVIATIONS | |||
| //************** | |||
| aapp $abbrev | |||
| abadv $abbrev | |||
| abc $abbrev | |||
| a.c 'as'e | |||
| adsl $abbrev | |||
| ae $abbrev | |||
| aids $abbrev | |||
| apedv $abbrev | |||
| avc $abbrev | |||
| bios b'i,OS | |||
| d.c d,es'e | |||
| cne $abbrev | |||
| cpu $abbrev | |||
| cpuc $abbrev | |||
| dpoc $abbrev | |||
| ecg $abbrev | |||
| edp $abbrev | |||
| aapp $abbrev | |||
| abadv $abbrev | |||
| abc $abbrev | |||
| a.c 'as'e | |||
| adsl $abbrev | |||
| ae $abbrev | |||
| aids $abbrev | |||
| apedv $abbrev | |||
| avc $abbrev | |||
| bios b'i,OS | |||
| d.c d,es'e | |||
| cne $abbrev | |||
| cpu $abbrev | |||
| cpuc $abbrev | |||
| dpoc $abbrev | |||
| ecg $abbrev | |||
| edp $abbrev | |||
| ?1 etc ,ets'Et:*& | |||
| ?2 etc ,ets'Ete*& | |||
| hiv $abbrev | |||
| (http ://) ag,atete'pe_ | |||
| icc $abbrev | |||
| ieee $abbrev // Institute of Electrical and Electronics Engineers | |||
| iss $abbrev | |||
| jpeg Z,Ot&p'Eg | |||
| mpeg ,Emp'Eg | |||
| nba $abbrev | |||
| nvda $abbrev | |||
| oms $abbrev | |||
| omt $abbrev | |||
| osi $abbrev | |||
| e.u.a Eua | |||
| eua $abbrev | |||
| fbi $abbrev | |||
| hiv $abbrev | |||
| (http ://) ag,atete'pe_ | |||
| icc $abbrev | |||
| ieee $abbrev // Institute of Electrical and Electronics Engineers | |||
| iss $abbrev | |||
| jpeg Z,Ot&p'Eg | |||
| mpeg ,Emp'Eg | |||
| nba $abbrev | |||
| nvda $abbrev | |||
| oms $abbrev | |||
| omt $abbrev | |||
| osi $abbrev | |||
| ?1 sa ,Esj'a | |||
| ?1 sos ,Esj,O'Es | |||
| ue $abbrev | |||
| unts $abbrev | |||
| usb $abbrev | |||
| ue $abbrev | |||
| unts $abbrev | |||
| usb $abbrev | |||
| dr $dot | |||
| @@ -596,48 +604,65 @@ governo gov'ernU $noun | |||
| // MAIN WORD DICTIONARY | |||
| //********************* | |||
| borboleta b,orbol'et& | |||
| catorze k&t'orzy | |||
| fosse f'osy | |||
| fossem f'oseIN | |||
| hoje 'oZi | |||
| líderes l'ide*ys | |||
| mexa m'eS& | |||
| mexi meS'i | |||
| mexo m'eSU | |||
| ?2 mulher mulj'Er | |||
| ?4 mulher mul^'Er | |||
| mui mu~j | |||
| muito m'u~jtu // -s is included as a suffix | |||
| muita m'u~jt& | |||
| praxedes pR&S'EdZys | |||
| ?2 rede x'edZy | |||
| selvagem seUv'aZeIN | |||
| teta t'et& | |||
| // $alt changes the first [o] phoneme to open [O] | |||
| novos $alt | |||
| mortos $alt | |||
| corpos $alt | |||
| modo $alt | |||
| modos $alt | |||
| fogos $alt | |||
| lopes $alt | |||
| jogos $alt | |||
| // Close [O] | |||
| ?1 calculadora k,Alkul&d'or& | |||
| ?1 professora pr,ufys'or& | |||
| ?1 senhora syn^'or& | |||
| ?1 sobre s'obry | |||
| // $alt changes stressed [e] or [o] phoneme to open [E] or [O] | |||
| // $alt2 changes stressed [E] or [O] phoneme to close [e] or [o] | |||
| boca $alt2 | |||
| borboleta $alt2 | |||
| catorze $alt2 | |||
| copo $alt | |||
| escova $alt2 | |||
| fosse $alt2 | |||
| fossem $alt2 | |||
| hoje $alt2 | |||
| líderes $alt2 | |||
| mexa m'eS& | |||
| mexi meS'i | |||
| mexo m'eSU | |||
| ?2 mulher mulj'Er | |||
| ?4 mulher mul^'Er | |||
| mui mwi | |||
| muito mw'iNtU // -s is included as a suffix | |||
| muita mw'iNt& | |||
| paexa paeSa | |||
| perdem $alt | |||
| preto $alt2 | |||
| onu $1 | |||
| rede $alt2 | |||
| rixa xiS& | |||
| selvagem seUv'aZeIN | |||
| suor swOr | |||
| tapete $alt2 | |||
| teta $alt2 | |||
| novos $alt | |||
| mortos $alt | |||
| corpos $alt | |||
| modo $alt | |||
| modos $alt | |||
| fogos $alt | |||
| lopes $alt | |||
| jogos $alt | |||
| doce $alt2 | |||
| drogas $alt | |||
| grosso $alt2 | |||
| torres $alt2 | |||
| // Close [o] | |||
| ?1 calculadora $alt2 | |||
| ?1 professora $alt2 | |||
| ?1 senhora $alt2 | |||
| ?1 sobre $alt2 | |||
| vanessa $alt2 | |||
| violeta $alt2 | |||
| abacaxi abakaSy | |||
| axé aSE | |||
| elixir eliSir | |||
| ?1 fixe f'iSy | |||
| roxo x'oSU | |||
| xiquexique S,ikeS'iky | |||
| // foreign words | |||
| ?1 alt 'alt | |||
| ?2 agosto &g'ostU | |||
| @@ -774,6 +799,7 @@ louis _^_FR | |||
| ?2 Outlook ,aUtl'uk | |||
| ?1 paint p'aint | |||
| ?1 player pl'eI&r- | |||
| playstation _^_EN | |||
| ?1 point p'oint | |||
| ?1 power p'aU&r- | |||
| ?1 product p:r'&d&kt | |||
| @@ -831,7 +857,7 @@ stephen st'i:v@n | |||
| steve st'i:v | |||
| turing t'u*iNg | |||
| voltaire vOlt'Er | |||
| von f'On | |||
| von f%On | |||
| // foreign common names/surnames | |||
+ 757
- 717
dictsource/pt_rules
File diff suppressed because it is too large
View File
+ 15
- 9
dictsource/ta_list
View File
| @@ -28,7 +28,7 @@ | |||
| ஸ் is | |||
| ஹ் iC | |||
| U+b82 anUsvVRV | |||
| ஃ ah | |||
| ஃ agH | |||
| U+bcd ot.RU | |||
| ஏ je: | |||
| @@ -165,15 +165,11 @@ _1M3x orUko:d.i | |||
| _0M3 ko:d.ie: | |||
| _1M3 orUko:d.ie: | |||
| _0M4x a:jirVmko:d.i // 10,000,000,000 | |||
| _1M4x a:jirVmko:d.i | |||
| _0M4 a:jirVmko:d.ie: | |||
| _1M4 a:jirVmko:d.ie: | |||
| _dpt _pul.l.i | |||
| _0M5 a:jirVma:jirVmko:d.i // 10,000,000,000,000 | |||
| _1M5 a:jirVma:jirVmko:d.i | |||
| _dpt _pul.l.i | |||
| // English words | |||
| tamil தமிழ் $text | |||
| // exceptions | |||
| @@ -204,6 +200,13 @@ _dpt _pul.l.i | |||
| பீடி $alt | |||
| பீதி $alt | |||
| பேகம் $alt | |||
| பார்லி $alt | |||
| பிக்கினி $alt | |||
| பேதம் $alt | |||
| போனஸ் $alt | |||
| போகி $alt | |||
| பாபா ba:ba: | |||
| புத்த buddV | |||
| // initial த as [d] | |||
| @@ -222,6 +225,10 @@ _dpt _pul.l.i | |||
| தடியன் $alt | |||
| தரிசனம் $alt | |||
| தட்சணை $alt | |||
| தைவதம் $alt | |||
| தாட்சண்யம் $alt | |||
| தனம் $alt | |||
| திக்கற்ற $alt | |||
| கக $alt // initial க as [g] | |||
| @@ -242,4 +249,3 @@ _dpt _pul.l.i | |||
| பப pVpV | |||
| டாக்டர் d.a:ktVr | |||
+ 215
- 76
dictsource/ta_rules
View File
| @@ -3,6 +3,7 @@ | |||
| // Spelling to phoneme rules for Tamil | |||
| // B means a combining vowel sign, or a virama | |||
| // K means a consonant or end-of-word | |||
| .replace | |||
| @@ -16,56 +17,28 @@ | |||
| ௭ 7 | |||
| ௮ 8 | |||
| ௯ 9 | |||
| ொ ொ | |||
| ோ ோ | |||
| ௌ ௌ | |||
| .group 0xe0ae // characters which start with UTF-8 bytes: [e0 ae] | |||
| ஂ // anusvara | |||
| ஃ // visarga | |||
| அ a | |||
| ஆ a: | |||
| இ i | |||
| ஈ i: | |||
| உ u | |||
| ஊ u: | |||
| எ e | |||
| _) எ ;e // add a short [j] sound at start of word ? | |||
| ஏ e: | |||
| _) ஏ ;e: // add a short [j] sound at start of word ? | |||
| ஐ aI | |||
| ஒ o | |||
| ஓ o: | |||
| ஔ aU | |||
| // consonants | |||
| .group க | |||
| க்ஷ ks.V | |||
| க்ஷ (B ks. | |||
| க gV // inter-vocalic, unless there is virama before or after | |||
| க (B g | |||
| க (் g | |||
| ்) க gV | |||
| ்) க (B g | |||
| _) க kV | |||
| _) க (B k | |||
| _) க (T gV // if word has $alt attribute in ta_list | |||
| _) க (BT g // $alt | |||
| க்க kkV | |||
| க்க (B kk | |||
| ற்) க _kV | |||
| ற்) க (B _k | |||
| க (ீத g | |||
| க (ஜ gV | |||
| @@ -92,50 +65,74 @@ | |||
| _) க (ுண g | |||
| _) க (தியில் gV | |||
| _) க (டிகார gV | |||
| வி) க்ட (ோரியா kt. // victoria | |||
| க (ோப g | |||
| க (ாரன k | |||
| க (ாரர k | |||
| _) க (ோபம k | |||
| _) கோப (ித்து ko:b | |||
| _) க (ோபப் k | |||
| _) க (ெட்டி g | |||
| .group ங | |||
| ங NV | |||
| ங (B N | |||
| .group ச | |||
| ச sV // ?? [z] | |||
| ச (B s | |||
| _) ச sa | |||
| _) ச sV | |||
| _) ச (B s | |||
| ச்ச tS:V | |||
| ச்ச (B tS: | |||
| ற்ச tS: | |||
| ற்ச (B tS: | |||
| ட்) ச tSV | |||
| ட்) ச (B tS | |||
| ற்) ச tSV | |||
| ற்) ச (B tS | |||
| ஞ்) ச dZV | |||
| ஞ்) ச (B dZ | |||
| ச் (_ tS | |||
| ச்_) ச tSV // previous word ends in ச் | |||
| ச்_) ச (B tS | |||
| _) ச (ிட் tS | |||
| _) ச (ின் tS | |||
| _) ச (ப்பாத்தி tSV | |||
| .group ஜ | |||
| ஜ dZV | |||
| ஜ (B dZ | |||
| .group ஞ | |||
| ஞ n^V | |||
| ஞ (B n^ | |||
| .group ட | |||
| ட d.V | |||
| ட (B d. | |||
| // _) ட t.V | |||
| // _) ட (B t. | |||
| _) ட (ீ t. | |||
| ட்ட t.t.V | |||
| ட்ட (B t.t. | |||
| ஷ்) ட t.V | |||
| ஷ்) ட (B t. | |||
| _) டாக்ட (ர d.a:kt.V | |||
| _) ட (ோக்கியோ t. | |||
| ிங்) ட (ன் t.V // -ington | |||
| _) ட (ாக்க t. // talkies | |||
| .group ண | |||
| ண n.V | |||
| ண (B n. | |||
| .group த | |||
| த dV | |||
| த (B d | |||
| _) த tV | |||
| @@ -149,27 +146,27 @@ | |||
| ஸ்) த tV | |||
| ஸ்) த (B t | |||
| // exceptions, த as [d] | |||
| _) த (ன dV | |||
| _) த (ர்ம dV | |||
| _) த (ுர் d | |||
| _) த (ூர d | |||
| _) த (ர்ம dV | |||
| _) த (ுர் d | |||
| _) த (ூர d | |||
| _) த (ெய்வ d | |||
| _) த (ுஷ் d | |||
| _) த (ுஷ் d | |||
| _) த (க்ஷிணா dV | |||
| _) த (ண்ட dV | |||
| _) த (ருமி dV | |||
| _) த (ர்பை dV | |||
| _) த (ண்ட dV | |||
| _) த (ருமி dV | |||
| _) த (ர்பை dV | |||
| _) த (ாவா d | |||
| _) த (ாதா d | |||
| _) த (ரித்திரம dV | |||
| _) த (ர்பார dV | |||
| _) த (ீர்க d | |||
| _) த (ர்பார dV | |||
| _) த (ீர்க d | |||
| _) த (ீரன d | |||
| _) த (ீரர் d | |||
| _) த (ீரச் d | |||
| _) த (ினுச d | |||
| _) த (ாராவி d | |||
| _) த (ர்க dV | |||
| _) த (ர்க dV | |||
| _) த (ான d | |||
| _) த (ேக d | |||
| _) த (ேக்கு t | |||
| @@ -177,12 +174,11 @@ | |||
| _) த (ேக்கடி t | |||
| _) த (ிரவிய d | |||
| _) த (ூப d | |||
| _) த (ீப d | |||
| _) த (ீர d | |||
| _) த (ீப d | |||
| _) த (ைரிய d | |||
| _) த (ிட d | |||
| _) த (ிட d | |||
| _) த (ிரவ d | |||
| _) த (ிடீ d | |||
| _) த (ிடீ d | |||
| _) த (ிவச d | |||
| _) த (ியான d | |||
| _) த (ானிய d | |||
| @@ -190,7 +186,7 @@ | |||
| _) த (ிகில d | |||
| _) த (ூம d | |||
| _) த (ாவணி d | |||
| _) த (ாம்_தூம d | |||
| _) த (ாம்_தூம d | |||
| _) த (ாடி d | |||
| _) த (ாச d | |||
| _) த (சரா dV | |||
| @@ -198,17 +194,52 @@ | |||
| _) த (ரணி dV | |||
| _) த (ாரணி d | |||
| _) த (ோசை d | |||
| _) த (வம dV | |||
| _) த (ட்சன dV | |||
| _) த (ாட்சாய d | |||
| _) த (ாக்கா d | |||
| _) த (ில்லி d | |||
| _) த (டித்த dV | |||
| _) த (டியன dV | |||
| _) த (டியர dV | |||
| _) த (ிக்கு d | |||
| _) த (ிக்கு_வாய t | |||
| _) த (ிக்கில d | |||
| _) த (னபால dV | |||
| _) த (னசேகரன dV | |||
| _) த (னலட்சுமி dV | |||
| _) த (னகோடி dV | |||
| _) த (னன்ஜெயன dV | |||
| _) த (ிசை d | |||
| _) த (சை dV | |||
| _) த (னராஜ dV | |||
| _) த (ன்மந்திரி dV | |||
| _) த (ினம d | |||
| _) த (ினக d | |||
| _) த (னலக்ஷ்மி dV | |||
| _) த (க்க்ஷிண dV | |||
| _) த (ட்சிண dV | |||
| _) த (ன்ராஜ dV | |||
| _) த (ாராபுர d | |||
| _) த (டி_மாட dV | |||
| பு) த்த (ி dd | |||
| பு) த்த (ியி dd | |||
| பு) த்த (ர ddV | |||
| பு) த்த (ன ddV | |||
| .group ந | |||
| ந nV | |||
| ந (B n // dental n | |||
| .group ன | |||
| ன nV | |||
| ன (B n // alveolar n | |||
| .group ப | |||
| ப bV | |||
| ப (B b | |||
| _) ப pV | |||
| @@ -221,20 +252,24 @@ | |||
| ட்) ப (B p | |||
| ற்) ப pV | |||
| ற்) ப (B p | |||
| று) ப pV | |||
| று) ப(B p | |||
| று) ப _pV | |||
| று) ப(B _p | |||
| ன்) ப pV | |||
| ன்) ப (B p | |||
| ம்) ப p | |||
| ம்) ப (ா p | |||
| ம்) ப (B b | |||
| த்) ப p | |||
| த்) ப (ா p | |||
| த்) ப (B b | |||
| ம) ப pV | |||
| ம) ப (ா p | |||
| ம) ப (B b | |||
| த) ப pV | |||
| த) ப (ா p | |||
| த) ப (B b | |||
| பத (ி pVt | |||
| ப (ுர p | |||
| ப (ால p | |||
| ப (ாள p | |||
| ம்) ப (ா b | |||
| ஃ) ப fV | |||
| ஃ) ப (B f | |||
| _) ப (ால b | |||
| _) ப (ால் p | |||
| @@ -273,59 +308,163 @@ | |||
| _) ப (லி bV | |||
| _) ப (கவான bV | |||
| _) ப (ௌதிக b | |||
| _) ப (ரோட bV | |||
| _) ப (ெர்லிங b | |||
| _) ப (ீஜிங b | |||
| _) ப (ுவன b | |||
| _) ப (ரதநாட்டிய bV | |||
| _) ப (ேதலித்த b | |||
| _) ப (ோன்ஸ்லே b | |||
| _) ப (ௌத்த b | |||
| _) ப (கீர bV | |||
| _) ப (கிரங்க bV | |||
| _) ப (ோபால b | |||
| _) ப (ெங்களூர b | |||
| _) ப (ூபாள b | |||
| _) ப (ுத்த b | |||
| _) ப (னியன bV | |||
| கோ) ப (ி p | |||
| // musical notes | |||
| சா) ப (ா p | |||
| ரி) ப (K pV | |||
| ரீ) ப (K pV | |||
| ரி) ப (ா p | |||
| ரீ) ப (ா p | |||
| ம) ப (K pV | |||
| மா) ப (K pV | |||
| ம) ப (ா p | |||
| மா) ப( ா p | |||
| பப (K pVpV | |||
| பாப (K pa:pV | |||
| பப (ா pVp | |||
| பாப (ா pa:p | |||
| // த) ப (K pV | |||
| தா) ப (K pV | |||
| // த) ப (ா p | |||
| தா) ப (ா p | |||
| னி) ப (K pV | |||
| னீ) ப (K pV | |||
| னி) ப (ா p | |||
| னீ) ப( ா p | |||
| க) ப (K pV | |||
| க) ப (ா p | |||
| கா) ப (K pV | |||
| கா) ப (ா p | |||
| // (exceptions) | |||
| தா) ப (ம் bV | |||
| _த) ப (ால b | |||
| _க) ப (ால b | |||
| _கா) ப (ந்து bV | |||
| .group ம | |||
| ம mV | |||
| ம (B m | |||
| .group ய | |||
| ய jV | |||
| ய (B j | |||
| .group ர | |||
| ர rV | |||
| ர (B r | |||
| .group ற | |||
| ற RV | |||
| ற (B R | |||
| ற் (ற t. // RR -> t.R | |||
| ற்ச tS: | |||
| ற்ச (B tS: | |||
| .group ல | |||
| ல lV | |||
| ல (B l | |||
| .group ள | |||
| ள l.V | |||
| ள (B l. | |||
| .group ழ | |||
| ழ z.V | |||
| ழ (B z. | |||
| .group வ | |||
| வ vV | |||
| வ (B v | |||
| .group ஶ | |||
| ஶ SV | |||
| ஶ (B S | |||
| .group ஷ | |||
| ஷ s.V | |||
| ஷ (B s. | |||
| .group ஸ | |||
| ஸ sV | |||
| ஸ (B s | |||
| .group ஹ | |||
| ஹ HV | |||
| ஹ (B H | |||
| க்ஷ ks.V | |||
| க்ஷ (B ks. | |||
| .group ஃ | |||
| ஃ h | |||
| ஃப fV | |||
| ஃப (B f | |||
| ஃத QdV | |||
| ஃத (B Qd | |||
| ஃக gQV | |||
| ஃக (B gQ | |||
| // vowel letters | |||
| .group 0xe0ae // characters which start with UTF-8 bytes: [e0 ae] | |||
| ஂ // anusvara | |||
| அ a | |||
| ஆ a: | |||
| இ i | |||
| _) இ (ரா // silent before 'raa' | |||
| ஈ i: | |||
| உ u | |||
| ஊ u: | |||
| எ e | |||
| _) எ ;e // add a short [j] sound at start of word ? | |||
| ஏ e: | |||
| _) ஏ ;e: // add a short [j] sound at start of word ? | |||
| ஐ aI | |||
| ஒ o | |||
| ஓ o: | |||
| ஔ aU | |||
| // combining vowels | |||
+ 15
- 8
docs/commands.html
View File
| @@ -58,7 +58,9 @@ or<br> | |||
| Or just type<br> | |||
| <strong>espeak</strong><br> | |||
| followed by text on subsequent lines. Each line is spoken when | |||
| RETURN is pressed.<br>Use <strong>espeak -x</strong> to see the corresponding phoneme codes. | |||
| RETURN is pressed. | |||
| <p> | |||
| Use <strong>espeak -x</strong> to see the corresponding phoneme codes. | |||
| <p> <hr> | |||
| <h3>2.2.2 The Command Line Options</h3> | |||
| <dl> | |||
| @@ -88,11 +90,15 @@ If neither -f nor --stdin is given, then the text input is taken from "text word | |||
| <dt> | |||
| <strong>-s <integer></strong><br> | |||
| <dd>Sets the speed in words-per-minute (approximate values for the default English voice, others may differ slightly). The default value is 170. I generally use a faster speed | |||
| of 190. Range 80 to 390. | |||
| of 190. Range 80 to 390. Larger value are rounded down to the maximum. | |||
| <p> | |||
| <dt> | |||
| <strong>-b</strong><br> | |||
| <dd>Indicates that the input text is not UTF-8, but the 8-bit character set which corresponds to the language (eg. Latin-2 for Polish). Without this option, eSpeak assumes text is UTF8, but will automatically switch to the 8-bit character set if it finds an illegal UTF8 sequence. That may give wrong results if some 8-bit character sequences look like valid UFT8 multibyte characters. | |||
| <strong>-b <integer></strong><br> | |||
| <dd>Input text character format.<p> | |||
| 1 UTF-8. This is the default.<p> | |||
| 2 The 8-bit character set which corresponds to the language (eg. Latin-2 for Polish).<p> | |||
| 4 16 bit Unicode.<p> | |||
| Without this option, eSpeak assumes text is UTF-8, but will automatically switch to the 8-bit character set if it finds an illegal UTF-8 sequence. | |||
| <p> | |||
| <dt> | |||
| <strong>-g <integer></strong><br> | |||
| @@ -130,7 +136,7 @@ Quiet. No sound is generated. This may be useful with the -x option. | |||
| <pre> espeak -vaf</pre> | |||
| To use the Afrikaans voice. A modifier after the voice name can be used to vary the tone of the voice, eg: | |||
| <pre> espeak -vaf+3</pre> | |||
| The variants are <code> +m1 +m2 +m3 +m4 +m5 +m6 </code> for male voices and <code> +f1 +f2 +f3 +f4 </code> which simulate female voices by using higher pitches. Other variants are <code>+croak</code> and <code>+whisper</code>. | |||
| The variants are <code> +m1 +m2 +m3 +m4 +m5 +m6 +m7</code> for male voices and <code> +f1 +f2 +f3 +f4 </code> which simulate female voices by using higher pitches. Other variants include <code>+croak</code> and <code>+whisper</code>. | |||
| <p> | |||
| <voice filename> is a file within the <code>espeak-data/voices</code> directory.<br> | |||
| <variant> is a file within the <code>espeak-data/voices/!v</code> directory.<p> | |||
| @@ -188,7 +194,7 @@ Used with <strong>-w</strong>, it starts a new WAV file every <code><minutes& | |||
| <strong>--voices [=<language code>]</strong><br> | |||
| <dd>Lists the available voices.<br> | |||
| If =<language code> is present then only those voices which are suitable for that language are listed.<br> | |||
| <code>--voices=mbrola</code> lists the voices which use mbrola diphone voices. These are not included in the <code>--voices</code> list<br> | |||
| <code>--voices=mbrola</code> lists the voices which use mbrola diphone voices. These are not included in the default <code>--voices</code> list<br> | |||
| <code>--voices=variant</code> lists the voice variants (voice modifiers).<br> | |||
| </dl> | |||
| @@ -205,7 +211,8 @@ As well as plain text, phoneme mnemonics can be used in the text input to <stron | |||
| eg: <code> espeak -v en "[[D,Is Iz sVm f@n'EtIk t'Ekst 'InpUt]]" </code><p> | |||
| This command will speak: "This is some phonetic text input". | |||
| </dl> | |||
| </body> | |||
| </b> | |||
| <hr> | |||
| <a href="http://sourceforge.net"><img src="http://sflogo.sourceforge.net/sflogo.php?group_id=159649&type=2" width="125" height="37" border="0" alt="SourceForge.net Logo" /></a> | |||
| </body> | |||
+ 13
- 6
docs/dictionary.html
View File
| @@ -88,13 +88,13 @@ The rules are organized in groups, each starting with a ".group" line: | |||
| A group for each letter or character. | |||
| <p> | |||
| <dt><strong>.group <2 characters></strong><br><dd> | |||
| Optional groups for some common 2 letter combinations. This is only needed, for efficiency, in cases where there are many rules for a particular letter. They would not be needed for a language which has regular spelling rules. | |||
| Optional groups for some common 2 letter combinations. This is only needed, for efficiency, in cases where there are many rules for a particular letter. They would not be needed for a language which has regular spelling rules. The first character can only be an ascii character (less than 0x80). | |||
| <p> | |||
| <dt><strong>.group</strong><br><dd> | |||
| A group for other characters which don't have their own group. | |||
| <p> | |||
| <dt><strong>.L<nn></strong><br><dd> | |||
| Defines a group of letter sequences, any of which can match with <strong>Lnn</strong> in a <strong>post</strong> rule (see below). <strong>nn</strong> is a 2 digit decimal number in the range 01 to 25. eg:<p> | |||
| Defines a group of letter sequences, any of which can match with <strong>Lnn</strong> in a <strong>pre</strong> or <strong>post</strong> rule (see below). <strong>nn</strong> is a 2 digit decimal number in the range 01 to 25. eg:<p> | |||
| <code>.L01 b bl br pl pr</code> | |||
| <p> | |||
| <dt><strong>.replace</strong><br><dd> | |||
| @@ -159,7 +159,11 @@ indicates that a word which ends in "th" is translated using the English transla | |||
| <td><strong>B H F G Y </strong></td> | |||
| <td>These may indicate other sets of characters (defined for a particular language).</td> | |||
| </tr> | |||
| <tr> | |||
| <tr> | |||
| <td><strong>L<nn></strong></td> | |||
| <td>Any of the sequence of characters defined as a letter group (see 4.3.1 above).</td> | |||
| </tr> | |||
| <tr> | |||
| <td><strong>D</strong></td> | |||
| <td>Any digit.</td> | |||
| </tr> | |||
| @@ -480,6 +484,10 @@ A word (or group of words) may be given one or more flags, either instead of, or | |||
| <td>$dot</td> | |||
| <td>Ignore a . after this word even when followed by a capital letter (eg. Mr. Dr. ).</td> | |||
| </tr> | |||
| <tr> | |||
| <td>$hasdot</td> | |||
| <td>Use this pronunciation if the word is followed by a dot. (This attribute also implies $dot).</td> | |||
| </tr> | |||
| <tr> | |||
| <td>$abbrev</td> | |||
| <td>This has two meanings.<br> 1. If there is no phoneme string: Speak the word as individual letters, even if it contains a vowel (eg. "abc" should be spoken as "a" "b" "c").<br>2. If there is a phoneme string: This word is capitalized because it is an abbreviation and capitalization does indicate emphasis (if the "emphasize all-caps" is on).</td> | |||
| @@ -587,13 +595,12 @@ _0 to _9 | |||
| <td>The numbers 0 to 9 | |||
| </tr> | |||
| <tr> | |||
| <td>_13<td>etc. Any pronunciations which are needed for specific numbers in the range _11 to _99 | |||
| <td>_13<td>etc. Any pronunciations which are needed for specific numbers in the range _10 to _99 | |||
| </tr> | |||
| <tr> | |||
| <td>_2X _3X<td>Twenty, thirty, etc., used to make numbers 10 to 99 | |||
| </tr> | |||
| <tr> | |||
| <td>_nn<td>Any two digit numbers with a special pronunciation (eg. _15 "fifteen"). | |||
| </tr> | |||
| <tr><TD>_0C<td>The word for "hundred"</td> | |||
| <tr><TD>_1C _2C<td>Special pronunciation for one hundred, two hundred, etc., if needed.</tr> | |||
| @@ -601,7 +608,7 @@ _0 to _9 | |||
| <tr><TD>_0M1<td>The word for "thousand"</tr> | |||
| <tr><TD>_0M2<td>The word for "million"</tr> | |||
| <tr><TD>_0M3<td>The word for 1000000000</tr> | |||
| <tr><TD>_1M1 _2M1<td>Special pronunciation for one thousand, two thousand, tc, if needed</td> | |||
| <tr><TD>_1M1 _2M1<td>Special pronunciation for one thousand, two thousand, etc, if needed</td> | |||
| <tr><TD>_0and<td>Word for "and" when speaking numbers (eg. "two hundred and twenty").</tr> | |||
| <tr><TD>_dpt<td>Word spoken for the decimnal point/comma</tr> | |||
| <tr><TD>_dpt2<td>Word spoken (if any) at the end of all the digits after a decimal point.</tr> | |||
+ 27
- 19
docs/index.html
View File
| @@ -17,8 +17,12 @@ | |||
| <div align="center"> | |||
| (email) jonsd at users dot sourceforge.net<br> | |||
| <a href="http://espeak.sf.net/download.html"><strong>Download</strong></a> | |||
| <a href="http://sourceforge.net/forum/?group_id=159649"><strong>Forum</strong></a> | |||
| <a href="http://sourceforge.net/projects/espeak/"><strong>eSpeak Sourceforge page</a> | |||
| | |||
| <a href="http://sourceforge.net/projects/espeak/"><strong>eSpeak Sourceforge page</a> | |||
| | |||
| <a href="http://sourceforge.net/forum/?group_id=159649"><strong>Forum</strong></a> | |||
| | |||
| <a href="http://sourceforge.net/mail/?group_id=159649"><strong>Mailing list</strong></a> | |||
| </div> | |||
| </td> | |||
| </tr> | |||
| @@ -40,32 +44,36 @@ | |||
| eSpeak is a compact open source software speech synthesizer for English and other languages, for Linux and Windows. | |||
| <a href="http://espeak.sourceforge.net/"><strong>http://espeak.sourceforge.net</strong></a> | |||
| <p> | |||
| eSpeak produces good quality English speech. It uses a different synthesis method from other open source TTS engines, and sounds quite different. It's perhaps not as natural or "smooth", but I find the articulation clearer and easier to listen to for long periods. | |||
| eSpeak uses a "formant synthesis" method. This allows many languages to be provided in a small size. The speech is clear, and can be used at high speeds, but is not as natural or smooth as larger synthesizers which are based on human speech recordings. | |||
| <p> | |||
| It can run as a command line program to speak text from a file or from stdin. A shared library version is also available. | |||
| eSpeak is available as: | |||
| <ul> | |||
| <li>A command line program (Linux and Windows) to speak text from a file or from stdin. | |||
| <li>A shared library version for use by other programs. (On Windows this is a DLL). | |||
| <li>A SAPI5 version for Windows, so it can be used with screen-readers and other programs that support the Windows SAPI5 interface. | |||
| <li>eSpeak has been ported to other platforms, including Solaris and Mac OSX. | |||
| </ul> | |||
| Features. | |||
| <ul> | |||
| <li>Includes different Voices, whose characteristics can be altered. | |||
| <li>Can produce speech output as a WAV file. | |||
| <li>SSML (Speech Synthesis Markup Language) is supported (not complete), and also HTML. | |||
| <li>Compact size. The program and its data, including many languages, totals about 1 Mbytes. | |||
| <li>Can translate text to phoneme codes, so it could be adapted as a front end for another speech synthesis engine. | |||
| <li>Potential for other languages. Several are included in varying stages of progress. Help from native speakers for these or other languages is welcomed. | |||
| <li>Development tools available for producing and tuning phoneme data. | |||
| <li>Written in C++. | |||
| <li>Compact size. The program and its data, including many languages, totals about 1.4 Mbytes. | |||
| <li>Can be used as a front-end to MBROLA diphone voices, see <a href="mbrola.html">mbrola.html</a>. eSpeak converts text to phonemes with pitch and length information. | |||
| <li>Can translate text into phoneme codes, so it could be adapted as a front end for another speech synthesis engine. | |||
| <li>Potential for other languages. Several are included in varying stages of progress. Help from native speakers for these or other languages is welcome. | |||
| <li>Development tools are available for producing and tuning phoneme data. | |||
| <li>Written in C. | |||
| </ul> | |||
| <p> | |||
| It works well as a "Talker" with the KDE text to speech system (KTTS), as an alternative to Festival for example. As such, it can speak text which has been selected into the clipboard, or directly from the Konqueror browser or the Kate editor. A Gnome Speech driver is now available. | |||
| <p> | |||
| I regularly use it to listen to blogs and news sites. I prefer the sound through a domestic stereo system rather than my small computer speakers. | |||
| <hr> | |||
| <strong>Windows Version</strong>. There are Windows SAPI5 and command-line versions of eSpeak. The SAPI5 version can be used with screen readers such as NVDA, JAWS, Supernova, and Window-Eyes.<br> | |||
| They are available as a Windows installer package from the <a href="download.html"><strong>eSpeak Download</strong></a> page.<p> | |||
| A Windows version of the espeakedit program is also available. | |||
| I regularly use eSpeak to listen to blogs and news sites. I prefer the sound through a domestic stereo system rather than small computer speakers, which can sound rather harsh. | |||
| <hr> | |||
| <strong>Languages</strong>. The eSpeak speech synthesizer supports several languages, however in most cases these are initial drafts and need more work to improve them. Assistance from native speakers is welcome for these, or other new languages. Please contact me if you want to help.<p> | |||
| eSpeak does text to speech synthesis for the following languages, some better than others. Afrikaans, Albanian, Armenian, Cantonese, Catalan, Croatian, Czech, Dutch, English, Esperanto, Finnish, French, German, Greek, Hindi, Hungarian, Icelandic, Indonesian, Italian, Kurdish, Latvian, Lojban, Macedonian, Mandarin, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Spanish, Swahili, Swedish, Tamil, Vietnamese, Welsh. See <a href="languages.html">Languages</a>. | |||
| <strong>Languages</strong>. The eSpeak speech synthesizer supports several languages, however in many cases these are initial drafts and need more work to improve them. Assistance from native speakers is welcome for these, or other new languages. Please contact me if you want to help.<p> | |||
| eSpeak does text to speech synthesis for the following languages, some better than others. Afrikaans, Albanian, Armenian, Cantonese, Catalan, Croatian, Czech, Danish, Dutch, English, Esperanto, Finnish, French, German, Greek, Hindi, Hungarian, Icelandic, Indonesian, Italian, Kurdish, Latvian, Lojban, Macedonian, Mandarin, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Spanish, Swahili, Swedish, Tamil, Turkish, Vietnamese, Welsh. | |||
| <hr> | |||
| The latest <strong>development version</strong> is at: | |||
| <a href="http://espeak.sf.net/test/latest.html">espeak.sf.net/test/latest.html</a>. | |||
| <hr> | |||
| <strong>espeakedit</strong> is a GUI program used to prepare and compile phoneme data. It is now available for download. Documentation is currently sparse, but if you want to use it to add or improve language support, let me know. | |||
| <hr> | |||
+ 20
- 19
phsource/compile_report
View File
| @@ -2,9 +2,9 @@ | |||
| new total | |||
| base 104 104 | |||
| base2 26 125 | |||
| en 50 150 | |||
| en 51 150 | |||
| en_n 32 150 | |||
| en_us 37 151 | |||
| en_us 36 151 | |||
| en_sc 39 152 | |||
| en_rp 34 150 | |||
| en_wm 31 150 | |||
| @@ -34,8 +34,8 @@ | |||
| es 9 125 | |||
| es_la 1 125 | |||
| ca 11 127 | |||
| pt 28 141 | |||
| pt_pt 20 141 | |||
| pt 30 142 | |||
| pt_pt 20 142 | |||
| ro 36 147 | |||
| el 8 125 | |||
| grc 12 129 | |||
| @@ -51,7 +51,7 @@ | |||
| id 15 127 | |||
| sq 35 128 | |||
| hy 24 120 | |||
| da 22 122 | |||
| da 20 119 | |||
| rw 15 132 | |||
| ml 13 154 | |||
| kn 15 154 | |||
| @@ -164,7 +164,8 @@ d/dr [*] base | |||
| [d.] bn | |||
| d/tap [*;] ro | |||
| d/tap1 [*] base | |||
| d/tap2 [t#] en_us | |||
| d/tap2 [t#] en | |||
| [*] pt | |||
| d/tap3 [*] base | |||
| d/tap4 [r] es | |||
| d/tap_i [*;] ro | |||
| @@ -197,7 +198,8 @@ d/xd_pzd [d;] pl | |||
| d/xdz [dz] pl | |||
| [dz] sq | |||
| [dz] hy | |||
| d/x_tap [t#] en_us | |||
| d/x_tap [t#] en | |||
| [*] pt | |||
| dzh/dzh [dZ] base | |||
| [dZ;] base | |||
| [dz;] base | |||
| @@ -624,12 +626,10 @@ r3/r_trill.wav [R2] base | |||
| [x] pt | |||
| r3/r_u [(u)] base | |||
| r3/r_uvl [r"] base | |||
| [R4] da | |||
| r3/r_uvl.wav [r"] base | |||
| [R] fr | |||
| [r] fr | |||
| [r/2] fr | |||
| [R4] da | |||
| r3/rx [*] base | |||
| [r/] base | |||
| [r/] af | |||
| @@ -645,12 +645,11 @@ r3/@tap [**] base | |||
| r3/@tap2 [**] base | |||
| r3/@tap_rfx [r.] base | |||
| r/a_ [r] da | |||
| r/aa [R6] da | |||
| r/aa [R] da | |||
| r/r [r] base | |||
| [r-] base | |||
| [r] en_sc | |||
| [r] de | |||
| [R5] da | |||
| r/_r [r] base | |||
| [r] en_sc | |||
| [r.] bn | |||
| @@ -1563,8 +1562,6 @@ vowel/a# [a/] base2 | |||
| [a2] en_sc | |||
| [a2] en_wi | |||
| [&] sr | |||
| [&] pt | |||
| [&/] pt | |||
| [a#] rw | |||
| [a/] rw | |||
| vowel/a_2 [a] base2 | |||
| @@ -1605,6 +1602,8 @@ vowel/a#_3 [a2] en | |||
| [a] hi | |||
| [a#] ru | |||
| [a#] ca | |||
| [&] pt | |||
| [&/] pt | |||
| [&] pt_pt | |||
| [&/] pt_pt | |||
| [a] zhy | |||
| @@ -1725,8 +1724,7 @@ vowel/ee_1 [E] base2 | |||
| [E:] sv | |||
| [E:] no | |||
| [e] zhy | |||
| vowel/ee_2 [E] en | |||
| [E] cy | |||
| vowel/ee_2 [E] cy | |||
| [E2] nl | |||
| [E] zh | |||
| [E#] ku | |||
| @@ -1739,6 +1737,7 @@ vowel/ee_3 [&] af | |||
| [E] pt | |||
| [E] vi | |||
| vowel/ee_4 [E] sq | |||
| vowel/ee_5 [E] en | |||
| vowel/ee_6 [&] sk | |||
| [E3] sv | |||
| [E] ku | |||
| @@ -1881,7 +1880,8 @@ vowel/ii# [Y] cy | |||
| [i] sq | |||
| [y] ml | |||
| [y] kn | |||
| vowel/ii_2 [i] zh | |||
| vowel/ii_2 [I] en | |||
| [i] zh | |||
| vowel/ii#_2 [y] pl | |||
| vowel/ii_3 [I] cy | |||
| [I] fi | |||
| @@ -1894,8 +1894,7 @@ vowel/ii_3 [I] cy | |||
| [I] bn | |||
| [I] pa | |||
| vowel/ii#_3 [I2] en_us | |||
| vowel/ii_4 [I] en | |||
| [I2] en | |||
| vowel/ii_4 [I2] en | |||
| [I] en_us | |||
| vowel/ii_5 [I] la | |||
| [i] zh | |||
| @@ -2073,6 +2072,7 @@ vowel/u [u:] en_wi | |||
| [u:] lv | |||
| [u:] cs | |||
| [U] la | |||
| [u2] pt | |||
| [u] id | |||
| [u] ml | |||
| [u:] ml | |||
| @@ -2448,11 +2448,12 @@ x/b [b] base | |||
| x/b_ [b] base | |||
| [b] fr | |||
| x/d [d] base | |||
| [t#] en_us | |||
| [t#] en | |||
| [d] fr | |||
| [d.] hi | |||
| [dh.] hi | |||
| [d] hr | |||
| [*] pt | |||
| [d] el | |||
| [d] is | |||
| [d] id | |||
BIN
phsource/d/tap2
View File
BIN
phsource/n/nr@
View File
BIN
phsource/n/nra
View File
BIN
phsource/n/nre
View File
BIN
phsource/n/nri
View File
BIN
phsource/n/nro
View File
BIN
phsource/n/nru
View File
+ 1
- 19
phsource/ph_danish
View File
| @@ -134,27 +134,9 @@ phoneme r // used for 'r' after a vowel (to create a diphthong) | |||
| lengthmod 7 | |||
| endphoneme | |||
| phoneme R6 // | |||
| phoneme R // | |||
| liquid | |||
| formants r/aa | |||
| lengthmod 7 | |||
| endphoneme | |||
| phoneme R4 // uvular trill [r"] without WAV | |||
| vcd uvl frc | |||
| formants r3/r_uvl+r3/r_uvl.wav%1 | |||
| before _ r3/r_uvl+r3/r_uvl.wav%1 | |||
| lengthmod 6 | |||
| endphoneme | |||
| phoneme R5 // English r | |||
| liquid starttype #r endtype #r | |||
| rhotic | |||
| length 100 | |||
| lengthmod 7 | |||
| beforenotvowel r/ | |||
| formants r/r | |||
| endphoneme | |||
+ 12
- 2
phsource/ph_english
View File
| @@ -27,6 +27,16 @@ phoneme t2 // [t] which doesn't reduce | |||
| endphoneme | |||
| phoneme t# // reduced [t] as in "city" | |||
| vcd alv stop | |||
| vowelin f1=1 f2=1700 -300 300 f3=-100 80 | |||
| vowelout f1=2 f2=1700 -300 300 f3=-100 80 | |||
| formants d/tap2+x/d%70 | |||
| after @ d/x_tap | |||
| lengthmod 5 | |||
| endphoneme | |||
| phoneme l | |||
| liquid | |||
| length 100 | |||
| @@ -118,7 +128,7 @@ endphoneme | |||
| phoneme E | |||
| vowel starttype (e) endtype (e) | |||
| length 140 | |||
| formants vowel/ee_2 | |||
| formants vowel/ee_5 | |||
| reduceto I 0 | |||
| endphoneme | |||
| @@ -126,7 +136,7 @@ endphoneme | |||
| phoneme I | |||
| vowel starttype (i) endtype (i) | |||
| length 130 | |||
| formants vowel/ii_4 | |||
| formants vowel/ii_2 | |||
| linkout ; | |||
| endphoneme | |||
+ 0
- 9
phsource/ph_english_us
View File
| @@ -293,12 +293,3 @@ phoneme r/ // used for [r] when not preceding a vowel | |||
| endphoneme | |||
| phoneme t# // reduced [t] as in "city" | |||
| vcd alv stop | |||
| vowelin f1=1 f2=1700 -300 300 f3=-100 80 | |||
| vowelout f1=2 f2=1700 -300 300 f3=-100 80 | |||
| formants d/tap2+x/d%70 | |||
| after @ d/x_tap | |||
| lengthmod 5 | |||
| endphoneme | |||
+ 1
- 1
phsource/ph_german
View File
| @@ -186,7 +186,7 @@ endphoneme | |||
| phoneme y | |||
| vowel starttype (u) endtype (u) | |||
| length 150 | |||
| length 130 | |||
| formants vowel/yy_4 | |||
| before * DFT+40 | |||
| endphoneme | |||
+ 7
- 0
phsource/ph_hungarian
View File
| @@ -49,6 +49,7 @@ endphoneme | |||
| phoneme i: | |||
| vowel starttype (i) endtype (i) | |||
| long | |||
| length 220 | |||
| formants vowel/i | |||
| // linkout ; | |||
| @@ -56,36 +57,42 @@ endphoneme | |||
| phoneme e: | |||
| vowel starttype (e) endtype (e) | |||
| long | |||
| length 240 | |||
| formants vowel/e_3 | |||
| endphoneme | |||
| phoneme a: | |||
| vowel starttype (a) endtype (a) | |||
| long | |||
| length 270 | |||
| formants vowel/a | |||
| endphoneme | |||
| phoneme o: | |||
| vowel starttype (o) endtype (o) | |||
| long | |||
| length 260 | |||
| formants vowel/o_2 | |||
| endphoneme | |||
| phoneme u: | |||
| vowel starttype (u) endtype (u) | |||
| long | |||
| length 240 | |||
| formants vowel/u_bck | |||
| endphoneme | |||
| phoneme y: | |||
| vowel starttype (u) endtype (u) | |||
| long | |||
| length 240 | |||
| formants vowel/y | |||
| endphoneme | |||
| phoneme Y: | |||
| vowel starttype (@) endtype (@) | |||
| long | |||
| length 260 | |||
| formants vowel/y# | |||
| endphoneme | |||
+ 24
- 5
phsource/ph_pt_brazil
View File
| @@ -37,7 +37,7 @@ endphoneme | |||
| phoneme &~ | |||
| vowel starttype (@) endtype (@) | |||
| length 200 | |||
| length 180 | |||
| formants vnasal/a#_n | |||
| // reduceto & 4 | |||
| endphoneme | |||
| @@ -60,14 +60,14 @@ endphoneme | |||
| phoneme & | |||
| vowel starttype (@) endtype (@) | |||
| length 180 | |||
| formants vowel/a# | |||
| formants vowel/a#_3 | |||
| endphoneme | |||
| phoneme &/ // Used for final "a" when next word starts with "a" | |||
| vowel starttype (@) endtype (@) | |||
| beforevowel NULL | |||
| length 180 | |||
| formants vowel/a# | |||
| formants vowel/a#_3 | |||
| endphoneme | |||
| @@ -94,7 +94,7 @@ endphoneme | |||
| phoneme y // this is the same as [i] for Brazil | |||
| vowel starttype (i) endtype (i) | |||
| length 150 | |||
| length 110 | |||
| formants vowel/ii_6 | |||
| linkout ; | |||
| endphoneme | |||
| @@ -122,9 +122,15 @@ phoneme u | |||
| formants vowel/u_bck | |||
| endphoneme | |||
| phoneme U | |||
| phoneme u2 // TEST | |||
| vowel starttype (u) endtype (u) | |||
| length 160 | |||
| formants vowel/u | |||
| endphoneme | |||
| phoneme U | |||
| vowel starttype (u) endtype (u) | |||
| length 140 | |||
| formants vowel/uu_bck | |||
| endphoneme | |||
| @@ -135,6 +141,7 @@ phoneme aI | |||
| vowel starttype (a) endtype (i) | |||
| length 230 | |||
| formants vdiph/ai | |||
| linkout ; | |||
| endphoneme | |||
| @@ -142,6 +149,7 @@ phoneme eI | |||
| vowel starttype (e) endtype (i) | |||
| length 210 | |||
| formants vdiph/ei | |||
| linkout ; | |||
| endphoneme | |||
| @@ -149,6 +157,7 @@ phoneme OI | |||
| vowel starttype (o) endtype (i) | |||
| length 230 | |||
| formants vdiph/0i | |||
| linkout ; | |||
| endphoneme | |||
| @@ -213,3 +222,13 @@ phoneme s# // This is [s] for Brazi;, [S] for Portugal | |||
| switchvoicing z | |||
| endphoneme | |||
| phoneme * | |||
| vcd alv stop | |||
| vowelin f1=1 f2=1700 -300 300 f3=0 80 | |||
| vowelout f1=2 f2=1700 -300 300 f3=0 80 | |||
| formants d/tap2+x/d%40 | |||
| after @ d/x_tap | |||
| lengthmod 6 | |||
| endphoneme | |||
BIN
phsource/vnasal/a#_n
View File
BIN
phsource/vowel/a#_3
View File
BIN
phsource/vowel/a_5
View File
BIN
phsource/vowel/e_8
View File
BIN
phsource/vowel/e_9
View File
BIN
phsource/vowel/ii_2
View File
BIN
phsource/vowel/o_8
View File
BIN
phsource/vowel/vowelchart.png
View File
BIN
phsource/vwl_fr/_r
View File
BIN
phsource/vwl_fr/r
View File
BIN
phsource/vwl_fr/r_
View File
BIN
phsource/vwl_fr/r_@
View File
BIN
phsource/vwl_fr/r_a
View File
BIN
phsource/vwl_fr/r_i
View File
BIN
phsource/vwl_fr/r_o
View File
BIN
phsource/vwl_fr/r_u
View File
BIN
phsource/vwl_fr/r_y
View File
BIN
phsource/vwl_fr/ra
View File
BIN
phsource/vwl_fr/re
View File
BIN
phsource/vwl_fr/ri
View File
BIN
phsource/vwl_fr/ro
View File
BIN
phsource/vwl_fr/ru
View File
BIN
phsource/vwl_fr/ry
View File
BIN
phsource/vwl_fr/tr
View File
BIN
phsource/vwl_fr/xr
View File
+ 20
- 8
platforms/windows/make_espeak.iss
View File
| @@ -2,7 +2,7 @@ | |||
| [Setup] | |||
| AppName=eSpeak | |||
| AppVerName=eSpeak version 1.41.01 | |||
| AppVerName=eSpeak version 1.42 | |||
| AppCopyright=Licensed under GNU General Public License version 3. (See file License.txt for details). | |||
| WindowVisible=yes | |||
| @@ -118,7 +118,7 @@ begin | |||
| $07: Result := 'de'; | |||
| $08: Result := 'el'; | |||
| $09: Result := 'en'; | |||
| $0a: Result := 'es-la'; | |||
| $0a: Result := 'es-la es-la+m3 es-la+f3'; | |||
| $0b: Result := 'fi'; | |||
| $0c: Result := 'fr'; | |||
| $0e: Result := 'hu'; | |||
| @@ -147,6 +147,7 @@ begin | |||
| $41: Result := 'sw'; | |||
| $49: Result := 'ta'; | |||
| $4b: Result := 'kn'; | |||
| $50: Result := 'mn'; | |||
| $52: Result := 'cy'; | |||
| $61: Result := 'ne'; | |||
| $87: Result := 'rw'; | |||
| @@ -154,9 +155,9 @@ begin | |||
| // is there a match on the full language code? | |||
| case language of | |||
| $40a: Result := 'es'; | |||
| $80a: Result := 'es-la es-la+f3 es-la+m3'; | |||
| $c0a: Result := 'es'; | |||
| $816: Result := 'pt-pt'; | |||
| $816: Result := 'pt-pt es-la'; | |||
| $41a: Result := 'hr'; | |||
| $81a: Result := 'sr'; | |||
| $c1a: Result := 'sr'; | |||
| @@ -207,6 +208,7 @@ begin | |||
| 'ko': value := $412; | |||
| 'lv': value := $426; | |||
| 'mk': value := $42f; | |||
| 'mn': value := $450; | |||
| 'ne': value := $461; | |||
| 'nl': value := $413; | |||
| 'no': value := $414; | |||
| @@ -406,10 +408,16 @@ procedure InitializeWizard; | |||
| var | |||
| lang: String; | |||
| voice2: String; | |||
| uilang: String; | |||
| begin | |||
| // Create the language selection page | |||
| UILanguage := GetUILanguage; | |||
| UIVoice := VoiceFromLanguage(UILanguage); | |||
| uilang := Format(' (Language code %x)',[UILanguage]); | |||
| lang := ActiveLanguage; | |||
| Page := CreateInputQueryPage(wpSelectDir,CustomMessage('v1'),CustomMessage('v2'),CustomMessage('v3')); | |||
| Page := CreateInputQueryPage(wpSelectDir,CustomMessage('v1'),CustomMessage('v2')+uilang,CustomMessage('v3')); | |||
| // Add items (False means it's not a password edit) | |||
| Page.Add('', False); | |||
| @@ -418,15 +426,19 @@ begin | |||
| Page.Add('', False); | |||
| Page.Add('', False); | |||
| UILanguage := GetUILanguage; | |||
| UIVoice := VoiceFromLanguage(UILanguage); | |||
| // Set initial values (optional) | |||
| if UIVoice = 'en' then | |||
| voice2 := 'en-us' | |||
| else | |||
| voice2 := 'en'; | |||
| Page.Values[0] := Format('%s %s %s',[UIVoice, UIVoice+'+f2', voice2]); | |||
| if Pos('+',UIVoice) = 0 then | |||
| Page.Values[0] := Format('%s %s',[UIVoice, UIVoice+'+f2']) | |||
| else | |||
| Page.Values[0] := Format('%s',[UIVoice]); | |||
| Page.Values[1] := Format('%s',[voice2]); | |||
| end; | |||
+ 1
- 1
platforms/windows/make_espeakedit.iss
View File
| @@ -1,7 +1,7 @@ | |||
| [Setup] | |||
| AppName=eSpeakEdit | |||
| AppVerName=eSpeakEdit version 1.41.02 | |||
| AppVerName=eSpeakEdit version 1.42 | |||
| DefaultDirName={pf}\eSpeak | |||
| DefaultGroupName=eSpeak | |||
| OutputBaseFilename=setup_espeakedit | |||
+ 22
- 23
platforms/windows/windows_dll/src/speak_lib.h
View File
| @@ -24,7 +24,6 @@ | |||
| /* This is the header file for the library version of espeak */ | |||
| /* */ | |||
| /*************************************************************/ | |||
| #define ESPEAK_API __declspec(dllexport) | |||
| #include <stdio.h> | |||
| @@ -152,7 +151,7 @@ typedef enum { | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API int espeak_Initialize(espeak_AUDIO_OUTPUT output, int buflength, const char *path, int options); | |||
| int espeak_Initialize(espeak_AUDIO_OUTPUT output, int buflength, const char *path, int options); | |||
| /* Must be called before any synthesis functions are called. | |||
| output: the audio data can either be played by eSpeak or passed back by the SynthCallback function. | |||
| @@ -171,7 +170,7 @@ typedef int (t_espeak_callback)(short*, int, espeak_EVENT*); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API void espeak_SetSynthCallback(t_espeak_callback* SynthCallback); | |||
| void espeak_SetSynthCallback(t_espeak_callback* SynthCallback); | |||
| /* Must be called before any synthesis functions are called. | |||
| This specifies a function in the calling program which is called when a buffer of | |||
| speech sound data has been produced. | |||
| @@ -199,7 +198,7 @@ int SynthCallback(short *wav, int numsamples, espeak_EVENT *events); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API void espeak_SetUriCallback(int (*UriCallback)(int, const char*, const char*)); | |||
| void espeak_SetUriCallback(int (*UriCallback)(int, const char*, const char*)); | |||
| /* This function may be called before synthesis functions are used, in order to deal with | |||
| <audio> tags. It specifies a callback function which is called when an <audio> element is | |||
| encountered and allows the calling program to indicate whether the sound file which | |||
| @@ -240,7 +239,7 @@ int UriCallback(int type, const char *uri, const char *base); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_Synth(const void *text, | |||
| espeak_ERROR espeak_Synth(const void *text, | |||
| size_t size, | |||
| unsigned int position, | |||
| espeak_POSITION_TYPE position_type, | |||
| @@ -296,7 +295,7 @@ ESPEAK_API espeak_ERROR espeak_Synth(const void *text, | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_Synth_Mark(const void *text, | |||
| espeak_ERROR espeak_Synth_Mark(const void *text, | |||
| size_t size, | |||
| const char *index_mark, | |||
| unsigned int end_position, | |||
| @@ -320,7 +319,7 @@ ESPEAK_API espeak_ERROR espeak_Synth_Mark(const void *text, | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_Key(const char *key_name); | |||
| espeak_ERROR espeak_Key(const char *key_name); | |||
| /* Speak the name of a keyboard key. | |||
| If key_name is a single character, it speaks the name of the character. | |||
| Otherwise, it speaks key_name as a text string. | |||
| @@ -334,7 +333,7 @@ ESPEAK_API espeak_ERROR espeak_Key(const char *key_name); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_Char(wchar_t character); | |||
| espeak_ERROR espeak_Char(wchar_t character); | |||
| /* Speak the name of the given character | |||
| Return: EE_OK: operation achieved | |||
| @@ -379,7 +378,7 @@ typedef enum { | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_SetParameter(espeak_PARAMETER parameter, int value, int relative); | |||
| espeak_ERROR espeak_SetParameter(espeak_PARAMETER parameter, int value, int relative); | |||
| /* Sets the value of the specified parameter. | |||
| relative=0 Sets the absolute value of the parameter. | |||
| relative=1 Sets a relative value of the parameter. | |||
| @@ -415,7 +414,7 @@ ESPEAK_API espeak_ERROR espeak_SetParameter(espeak_PARAMETER parameter, int valu | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API int espeak_GetParameter(espeak_PARAMETER parameter, int current); | |||
| int espeak_GetParameter(espeak_PARAMETER parameter, int current); | |||
| /* current=0 Returns the default value of the specified parameter. | |||
| current=1 Returns the current value of the specified parameter, as set by SetParameter() | |||
| */ | |||
| @@ -423,7 +422,7 @@ ESPEAK_API int espeak_GetParameter(espeak_PARAMETER parameter, int current); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_SetPunctuationList(const wchar_t *punctlist); | |||
| espeak_ERROR espeak_SetPunctuationList(const wchar_t *punctlist); | |||
| /* Specified a list of punctuation characters whose names are to be spoken when the | |||
| value of the Punctuation parameter is set to "some". | |||
| @@ -438,7 +437,7 @@ ESPEAK_API espeak_ERROR espeak_SetPunctuationList(const wchar_t *punctlist); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API void espeak_SetPhonemeTrace(int value, FILE *stream); | |||
| void espeak_SetPhonemeTrace(int value, FILE *stream); | |||
| /* Controls the output of phoneme symbols for the text | |||
| value=0 No phoneme output (default) | |||
| value=1 Output the translated phoneme symbols for the text | |||
| @@ -450,7 +449,7 @@ ESPEAK_API void espeak_SetPhonemeTrace(int value, FILE *stream); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API void espeak_CompileDictionary(const char *path, FILE *log, int flags); | |||
| void espeak_CompileDictionary(const char *path, FILE *log, int flags); | |||
| /* Compile pronunciation dictionary for a language which corresponds to the currently | |||
| selected voice. The required voice should be selected before calling this function. | |||
| @@ -503,19 +502,19 @@ typedef struct { | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API const espeak_VOICE **espeak_ListVoices(espeak_VOICE *voice_spec); | |||
| const espeak_VOICE **espeak_ListVoices(espeak_VOICE *voice_spec); | |||
| /* Reads the voice files from espeak-data/voices and creates an array of espeak_VOICE pointers. | |||
| The list is terminated by a NULL pointer | |||
| If voice_spec is NULL then all voices are listed. | |||
| If voice spec is give, then only the voices which are compatible with the voice_spec | |||
| If voice spec is given, then only the voices which are compatible with the voice_spec | |||
| are listed, and they are listed in preference order. | |||
| */ | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_SetVoiceByName(const char *name); | |||
| espeak_ERROR espeak_SetVoiceByName(const char *name); | |||
| /* Searches for a voice with a matching "name" field. Language is not considered. | |||
| "name" is a UTF8 string. | |||
| @@ -528,7 +527,7 @@ ESPEAK_API espeak_ERROR espeak_SetVoiceByName(const char *name); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_SetVoiceByProperties(espeak_VOICE *voice_spec); | |||
| espeak_ERROR espeak_SetVoiceByProperties(espeak_VOICE *voice_spec); | |||
| /* An espeak_VOICE structure is used to pass criteria to select a voice. Any of the following | |||
| fields may be set: | |||
| @@ -548,7 +547,7 @@ ESPEAK_API espeak_ERROR espeak_SetVoiceByProperties(espeak_VOICE *voice_spec); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_VOICE *espeak_GetCurrentVoice(void); | |||
| espeak_VOICE *espeak_GetCurrentVoice(void); | |||
| /* Returns the espeak_VOICE data for the currently selected voice. | |||
| This is not affected by temporary voice changes caused by SSML elements such as <voice> and <s> | |||
| */ | |||
| @@ -556,7 +555,7 @@ ESPEAK_API espeak_VOICE *espeak_GetCurrentVoice(void); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_Cancel(void); | |||
| espeak_ERROR espeak_Cancel(void); | |||
| /* Stop immediately synthesis and audio output of the current text. When this | |||
| function returns, the audio output is fully stopped and the synthesizer is ready to | |||
| synthesize a new message. | |||
| @@ -569,14 +568,14 @@ ESPEAK_API espeak_ERROR espeak_Cancel(void); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API int espeak_IsPlaying(void); | |||
| int espeak_IsPlaying(void); | |||
| /* Returns 1 if audio is played, 0 otherwise. | |||
| */ | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_Synchronize(void); | |||
| espeak_ERROR espeak_Synchronize(void); | |||
| /* This function returns when all data have been spoken. | |||
| Return: EE_OK: operation achieved | |||
| EE_INTERNAL_ERROR. | |||
| @@ -585,7 +584,7 @@ ESPEAK_API espeak_ERROR espeak_Synchronize(void); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API espeak_ERROR espeak_Terminate(void); | |||
| espeak_ERROR espeak_Terminate(void); | |||
| /* last function to be called. | |||
| Return: EE_OK: operation achieved | |||
| EE_INTERNAL_ERROR. | |||
| @@ -595,7 +594,7 @@ ESPEAK_API espeak_ERROR espeak_Terminate(void); | |||
| #ifdef __cplusplus | |||
| extern "C" | |||
| #endif | |||
| ESPEAK_API const char *espeak_Info(void* ptr); | |||
| const char *espeak_Info(void* ptr); | |||
| /* Returns the version number string. | |||
| The parameter is for future use, and should be set to NULL | |||
| */ | |||
+ 1
- 0
platforms/windows/windows_dll/src/speech.h
View File
| @@ -30,6 +30,7 @@ | |||
| #define PATHSEP '\\' | |||
| // #define USE_PORTAUDIO | |||
| #define NO_VARIADIC_MACROS | |||
| #define ESPEAK_API __declspec(dllexport) | |||
| #define LIBRARY | |||
+ 5
- 5
platforms/windows/windows_sapi/version.rc2
View File
| @@ -5,8 +5,8 @@ | |||
| // | |||
| VS_VERSION_INFO VERSIONINFO | |||
| FILEVERSION 1,0,40,00 | |||
| PRODUCTVERSION 1,0,40,00 | |||
| FILEVERSION 1,0,42,00 | |||
| PRODUCTVERSION 1,0,42,00 | |||
| FILEFLAGSMASK 0x3fL | |||
| #ifdef _DEBUG | |||
| FILEFLAGS 0x1L | |||
| @@ -24,14 +24,14 @@ BEGIN | |||
| VALUE "Comments", "\0" | |||
| VALUE "CompanyName", "Jonathan Duddington\0" | |||
| VALUE "FileDescription", "Text to Speech\0" | |||
| VALUE "FileVersion", "1, 0,40,00\0" | |||
| VALUE "InternalName", "espeak1.40\0" | |||
| VALUE "FileVersion", "1, 0,42,00\0" | |||
| VALUE "InternalName", "espeak1.42\0" | |||
| VALUE "LegalCopyright", "Copyright (c) Jonathan Duddington\0" | |||
| VALUE "LegalTrademarks", "\0" | |||
| VALUE "OriginalFilename", "espeak_sapi.dll\0" | |||
| VALUE "PrivateBuild", "\0" | |||
| VALUE "ProductName", "espeak TTS\0" | |||
| VALUE "ProductVersion", "1, 0, 40, 00\0" | |||
| VALUE "ProductVersion", "1, 0, 42, 00\0" | |||
| VALUE "SpecialBuild", "\0" | |||
| END | |||
| END | |||
+ 38
- 6
src/compiledict.cpp
View File
| @@ -83,7 +83,6 @@ MNEM_TAB mnem_flags[] = { | |||
| {"$unstressend",13}, /* reduce stress at end of clause */ | |||
| {"$atend", 14}, /* use this pronunciation if at end of clause */ | |||
| {"$dot", 16}, /* ignore '.' after this word (abbreviation) */ | |||
| {"$abbrev", 17}, /* use this pronuciation rather than split into letters */ | |||
| {"$stem", 18}, // must have a suffix | |||
| @@ -93,6 +92,9 @@ MNEM_TAB mnem_flags[] = { | |||
| {"$alt2", 21}, | |||
| {"$combine", 22}, // Combine with the next word | |||
| {"$dot", 24}, // ignore '.' after this word (abbreviation) | |||
| {"$hasdot", 25}, // use this pronunciation if there is a dot after the word | |||
| {"$max3", 27}, // limit to 3 repetitions | |||
| {"$brk", 28}, // a shorter $pause | |||
| {"$text", 29}, // word translates to replcement text, not phonemes | |||
| @@ -125,6 +127,7 @@ typedef struct { | |||
| char name[LEN_GROUP_NAME+1]; | |||
| unsigned int start; | |||
| unsigned int length; | |||
| int group3_ix; | |||
| } RGROUP; | |||
| @@ -345,7 +348,7 @@ step=1; // TEST | |||
| break; | |||
| case 1: | |||
| if((c == '-') && (word[0] != '_')) | |||
| if((c == '-') && multiple_words) | |||
| { | |||
| if(isdigit(word[0])) | |||
| { | |||
| @@ -734,6 +737,7 @@ static char rule_post[80]; | |||
| static char rule_match[80]; | |||
| static char rule_phonemes[80]; | |||
| static char group_name[LEN_GROUP_NAME+1]; | |||
| static int group3_ix; | |||
| #define N_RULES 2000 // max rules for each group | |||
| @@ -1129,7 +1133,10 @@ static int __cdecl string_sorter(char **a, char **b) | |||
| static int __cdecl rgroup_sorter(RGROUP *a, RGROUP *b) | |||
| {//=================================================== | |||
| // Sort long names before short names | |||
| int ix; | |||
| ix = strlen(b->name) - strlen(a->name); | |||
| if(ix != 0) return(ix); | |||
| ix = strcmp(a->name,b->name); | |||
| if(ix != 0) return(ix); | |||
| return(a->start-b->start); | |||
| @@ -1401,6 +1408,7 @@ static int compile_dictrules(FILE *f_in, FILE *f_out, char *fname_temp) | |||
| int n_rules=0; | |||
| int count=0; | |||
| int different; | |||
| int wc; | |||
| const char *prev_rgroup_name; | |||
| unsigned int char_code; | |||
| int compile_mode=0; | |||
| @@ -1409,6 +1417,7 @@ static int compile_dictrules(FILE *f_in, FILE *f_out, char *fname_temp) | |||
| char *rules[N_RULES]; | |||
| int n_rgroups = 0; | |||
| int n_groups3 = 0; | |||
| RGROUP rgroup[N_RULE_GROUP2]; | |||
| linenum = 0; | |||
| @@ -1436,6 +1445,7 @@ static int compile_dictrules(FILE *f_in, FILE *f_out, char *fname_temp) | |||
| if(n_rules > 0) | |||
| { | |||
| strcpy(rgroup[n_rgroups].name,group_name); | |||
| rgroup[n_rgroups].group3_ix = group3_ix; | |||
| rgroup[n_rgroups].start = ftell(f_temp); | |||
| output_rule_group(f_temp,n_rules,rules,group_name); | |||
| rgroup[n_rgroups].length = ftell(f_temp) - rgroup[n_rgroups].start; | |||
| @@ -1481,7 +1491,8 @@ static int compile_dictrules(FILE *f_in, FILE *f_out, char *fname_temp) | |||
| while((*p > ' ') && (ix < LEN_GROUP_NAME)) | |||
| group_name[ix++] = *p++; | |||
| group_name[ix]=0; | |||
| group3_ix = 0; | |||
| if(sscanf(group_name,"0x%x",&char_code)==1) | |||
| { | |||
| // group character is given as a character code (max 16 bits) | |||
| @@ -1494,8 +1505,19 @@ static int compile_dictrules(FILE *f_in, FILE *f_out, char *fname_temp) | |||
| *p++ = char_code; | |||
| *p = 0; | |||
| } | |||
| else | |||
| { | |||
| if(translator->letter_bits_offset > 0) | |||
| { | |||
| utf8_in(&wc, group_name); | |||
| if(((ix = (wc - translator->letter_bits_offset)) >= 0) && (ix < 128)) | |||
| { | |||
| group3_ix = ix+1; // not zero | |||
| } | |||
| } | |||
| } | |||
| if(strlen(group_name) > 2) | |||
| if((group3_ix == 0) && (strlen(group_name) > 2)) | |||
| { | |||
| if(utf8_in(&c,group_name) < 2) | |||
| { | |||
| @@ -1573,7 +1595,17 @@ static int compile_dictrules(FILE *f_in, FILE *f_out, char *fname_temp) | |||
| if(gp > 0) | |||
| fputc(RULE_GROUP_END,f_out); | |||
| fputc(RULE_GROUP_START,f_out); | |||
| fprintf(f_out, prev_rgroup_name = rgroup[gp].name); | |||
| if(rgroup[gp].group3_ix != 0) | |||
| { | |||
| n_groups3++; | |||
| fputc(1,f_out); | |||
| fputc(rgroup[gp].group3_ix, f_out); | |||
| } | |||
| else | |||
| { | |||
| fprintf(f_out, "%s", prev_rgroup_name = rgroup[gp].name); | |||
| } | |||
| fputc(0,f_out); | |||
| } | |||
| @@ -1593,7 +1625,7 @@ static int compile_dictrules(FILE *f_in, FILE *f_out, char *fname_temp) | |||
| fclose(f_temp); | |||
| remove(fname_temp); | |||
| fprintf(f_log,"\t%d rules, %d groups\n\n",count,n_rgroups); | |||
| fprintf(f_log,"\t%d rules, %d groups (%d)\n\n",count,n_rgroups,n_groups3); | |||
| return(0); | |||
| } // end of compile_dictrules | |||
+ 72
- 59
src/dictionary.cpp
View File
| @@ -36,6 +36,7 @@ | |||
| #include "translate.h" | |||
| int dictionary_skipwords; | |||
| char dictionary_name[40]; | |||
| @@ -146,6 +147,7 @@ static void InitGroups(Translator *tr) | |||
| tr->groups2_start[ix]=255; // indicates "not set" | |||
| } | |||
| memset(tr->letterGroups,0,sizeof(tr->letterGroups)); | |||
| memset(tr->groups3,0,sizeof(tr->groups3)); | |||
| p = tr->data_dictrules; | |||
| while(*p != 0) | |||
| @@ -194,7 +196,8 @@ static void InitGroups(Translator *tr) | |||
| len = strlen(p); | |||
| p_name = p; | |||
| c = p_name[0]; | |||
| c2 = p_name[1]; | |||
| p += (len+1); | |||
| if(len == 1) | |||
| { | |||
| @@ -206,13 +209,18 @@ static void InitGroups(Translator *tr) | |||
| tr->groups1[0] = p; | |||
| } | |||
| else | |||
| if(c == 1) | |||
| { | |||
| // index by offset from letter base | |||
| tr->groups3[c2 - 1] = p; | |||
| } | |||
| else | |||
| { | |||
| if(tr->groups2_start[c] == 255) | |||
| tr->groups2_start[c] = tr->n_groups2; | |||
| tr->groups2_count[c]++; | |||
| tr->groups2[tr->n_groups2] = p; | |||
| c2 = p_name[1]; | |||
| tr->groups2_name[tr->n_groups2++] = (c + (c2 << 8)); | |||
| } | |||
| } | |||
| @@ -1255,18 +1263,17 @@ void SetWordStress(Translator *tr, char *output, unsigned int *dictionary_flags, | |||
| { | |||
| /* no explicit stress - stress the final vowel */ | |||
| stressed_syllable = vowel_count - 1; | |||
| if(max_stress == 0) | |||
| while(stressed_syllable > 0) | |||
| { | |||
| while(stressed_syllable > 0) | |||
| // find the last vowel which is not unstressed | |||
| if(vowel_stress[stressed_syllable] == 0) | |||
| { | |||
| if(vowel_stress[stressed_syllable] == 0) | |||
| { | |||
| vowel_stress[stressed_syllable] = 4; | |||
| break; | |||
| } | |||
| else | |||
| stressed_syllable--; | |||
| vowel_stress[stressed_syllable] = 4; | |||
| break; | |||
| } | |||
| else | |||
| stressed_syllable--; | |||
| } | |||
| max_stress = 4; | |||
| } | |||
| @@ -1391,7 +1398,7 @@ void SetWordStress(Translator *tr, char *output, unsigned int *dictionary_flags, | |||
| if(vowel_stress[2] == 4) | |||
| vowel_stress[1] = 3; | |||
| } | |||
| #if deleted | |||
| if((stressflags & 0x2000) && (vowel_stress[1] == 0)) | |||
| { | |||
| // If there is only one syllable before the primary stress, give it a secondary stress | |||
| @@ -1400,7 +1407,6 @@ void SetWordStress(Translator *tr, char *output, unsigned int *dictionary_flags, | |||
| vowel_stress[1] = 3; | |||
| } | |||
| } | |||
| #endif | |||
| done = 0; | |||
| for(v=1; v<vowel_count; v++) | |||
| @@ -1621,8 +1627,8 @@ void SetWordStress(Translator *tr, char *output, unsigned int *dictionary_flags, | |||
| #ifdef LOG_TRANSLATE | |||
| static char *DecodeRule(const char *group, char *rule) | |||
| {//================================================== | |||
| static char *DecodeRule(const char *group_chars, int group_length, char *rule) | |||
| {//=========================================================================== | |||
| /* Convert compiled match template to ascii */ | |||
| unsigned char rb; | |||
| @@ -1648,7 +1654,13 @@ static char *DecodeRule(const char *group, char *rule) | |||
| match_type = 0; | |||
| buf_pre[0] = 0; | |||
| strcpy(buf,group); | |||
| for(ix=0; ix<group_length; ix++) | |||
| { | |||
| buf[ix] = group_chars[ix]; | |||
| } | |||
| buf[ix] = 0; | |||
| p = &buf[strlen(buf)]; | |||
| while(!finished) | |||
| { | |||
| @@ -1819,8 +1831,8 @@ void AppendPhonemes(Translator *tr, char *string, int size, const char *ph) | |||
| static void MatchRule(Translator *tr, char *word[], const char *group, char *rule, MatchRecord *match_out, int word_flags, int dict_flags) | |||
| {//======================================================================================================================================= | |||
| static void MatchRule(Translator *tr, char *word[], int group_length, char *rule, MatchRecord *match_out, int word_flags, int dict_flags) | |||
| {//====================================================================================================================================== | |||
| /* Checks a specified word against dictionary rules. | |||
| Returns with phoneme code string, or NULL if no match found. | |||
| @@ -1865,12 +1877,12 @@ static void MatchRule(Translator *tr, char *word[], const char *group, char *rul | |||
| static MatchRecord best; | |||
| int total_consumed; /* letters consumed for best match */ | |||
| int group_length; | |||
| unsigned char condition_num; | |||
| char *common_phonemes; /* common to a group of entries */ | |||
| char *group_chars; | |||
| group_chars = *word; | |||
| if(rule == NULL) | |||
| { | |||
| @@ -1890,8 +1902,6 @@ static void MatchRule(Translator *tr, char *word[], const char *group, char *rul | |||
| best.end_type = 0; | |||
| best.del_fwd = NULL; | |||
| group_length = strlen(group); | |||
| /* search through dictionary rules */ | |||
| while(rule[0] != RULE_GROUP_END) | |||
| { | |||
| @@ -2372,7 +2382,7 @@ static void MatchRule(Translator *tr, char *word[], const char *group, char *rul | |||
| if(group_length > 1) | |||
| pts += 35; // to account for an extra letter matching | |||
| DecodePhonemes(match.phonemes,decoded_phonemes); | |||
| fprintf(f_trans,"%3d\t%s [%s]\n",pts,DecodeRule(group,rule_start),decoded_phonemes); | |||
| fprintf(f_trans,"%3d\t%s [%s]\n",pts,DecodeRule(group_chars, group_length, rule_start),decoded_phonemes); | |||
| } | |||
| #endif | |||
| @@ -2411,7 +2421,7 @@ int TranslateRules(Translator *tr, char *p_start, char *phonemes, int ph_size, c | |||
| Append the result to 'phonemes' and any standard prefix/suffix in 'end_phonemes' */ | |||
| unsigned char c, c2; | |||
| unsigned int c12; | |||
| unsigned int c12, c123; | |||
| int wc=0; | |||
| int wc_prev; | |||
| int wc_bytes; | |||
| @@ -2432,8 +2442,6 @@ int TranslateRules(Translator *tr, char *p_start, char *phonemes, int ph_size, c | |||
| char word_copy[N_WORD_BYTES]; | |||
| static const char str_pause[2] = {phonPAUSE_NOLINK,0}; | |||
| char group_name[4]; | |||
| if(tr->data_dictrules == NULL) | |||
| return(0); | |||
| @@ -2502,12 +2510,22 @@ int TranslateRules(Translator *tr, char *p_start, char *phonemes, int ph_size, c | |||
| { | |||
| digit_count = 0; | |||
| found = 0; | |||
| if(n > 0) | |||
| if(((ix = wc - tr->letter_bits_offset) >= 0) && (ix < 128)) | |||
| { | |||
| if(tr->groups3[ix] != NULL) | |||
| { | |||
| MatchRule(tr, &p, wc_bytes, tr->groups3[ix], &match1, word_flags, dict_flags0); | |||
| found = 1; | |||
| } | |||
| } | |||
| if(!found && (n > 0)) | |||
| { | |||
| /* there are some 2 byte chains for this initial letter */ | |||
| c2 = p[1]; | |||
| c12 = c + (c2 << 8); /* 2 characters */ | |||
| c123 = c12 + (p[2] << 16); | |||
| g1 = tr->groups2_start[c]; | |||
| for(g=g1; g < (g1+n); g++) | |||
| @@ -2516,17 +2534,13 @@ int TranslateRules(Translator *tr, char *p_start, char *phonemes, int ph_size, c | |||
| { | |||
| found = 1; | |||
| group_name[0] = c; | |||
| group_name[1] = c2; | |||
| group_name[2] = 0; | |||
| p2 = p; | |||
| MatchRule(tr, &p2, group_name, tr->groups2[g], &match2, word_flags, dict_flags0); | |||
| MatchRule(tr, &p2, 2, tr->groups2[g], &match2, word_flags, dict_flags0); | |||
| if(match2.points > 0) | |||
| match2.points += 35; /* to acount for 2 letters matching */ | |||
| /* now see whether single letter chain gives a better match ? */ | |||
| group_name[1] = 0; | |||
| MatchRule(tr, &p, group_name, tr->groups1[c], &match1, word_flags, dict_flags0); | |||
| MatchRule(tr, &p, 1, tr->groups1[c], &match1, word_flags, dict_flags0); | |||
| if(match2.points >= match1.points) | |||
| { | |||
| @@ -2541,15 +2555,12 @@ int TranslateRules(Translator *tr, char *p_start, char *phonemes, int ph_size, c | |||
| if(!found) | |||
| { | |||
| /* alphabetic, single letter chain */ | |||
| group_name[0] = c; | |||
| group_name[1] = 0; | |||
| if(tr->groups1[c] != NULL) | |||
| MatchRule(tr, &p, group_name, tr->groups1[c], &match1, word_flags, dict_flags0); | |||
| MatchRule(tr, &p, 1, tr->groups1[c], &match1, word_flags, dict_flags0); | |||
| else | |||
| { | |||
| // no group for this letter, use default group | |||
| MatchRule(tr, &p, "", tr->groups1[0], &match1, word_flags, dict_flags0); | |||
| MatchRule(tr, &p, 0, tr->groups1[0], &match1, word_flags, dict_flags0); | |||
| if((match1.points == 0) && ((option_sayas & 0x10) == 0)) | |||
| { | |||
| @@ -2715,9 +2726,8 @@ void ApplySpecialAttribute2(Translator *tr, char *phonemes, int dict_flags) | |||
| len = strlen(phonemes); | |||
| switch(tr->translator_name) | |||
| if(tr->langopts.param[LOPT_ALT] & 2) | |||
| { | |||
| case L('i','t'): | |||
| for(ix=0; ix<(len-1); ix++) | |||
| { | |||
| if(phonemes[ix] == phonSTRESS_P) | |||
| @@ -2740,7 +2750,6 @@ void ApplySpecialAttribute2(Translator *tr, char *phonemes, int dict_flags) | |||
| break; | |||
| } | |||
| } | |||
| break; | |||
| } | |||
| } // end of ApplySpecialAttribute2 | |||
| @@ -2749,9 +2758,7 @@ void ApplySpecialAttribute(Translator *tr, char *phonemes, int dict_flags) | |||
| {//======================================================================= | |||
| // Amend the translated phonemes according to an attribute which is specific for the language. | |||
| int len; | |||
| int ix; | |||
| char *p_end; | |||
| int phoneme_1; | |||
| if((dict_flags & (FLAG_ALT_TRANS | FLAG_ALT2_TRANS)) == 0) | |||
| return; | |||
| @@ -2772,18 +2779,6 @@ void ApplySpecialAttribute(Translator *tr, char *phonemes, int dict_flags) | |||
| } | |||
| break; | |||
| case L('p','t'): | |||
| phoneme_1 = PhonemeCode('o'); | |||
| for(ix=0; ix<(len-1); ix++) | |||
| { | |||
| if(phonemes[ix] == phoneme_1) | |||
| { | |||
| phonemes[ix] = PhonemeCode('O'); | |||
| break; | |||
| } | |||
| } | |||
| break; | |||
| case L('r','o'): | |||
| if(p_end[0] == PhonemeCode('j')) | |||
| { | |||
| @@ -2961,6 +2956,7 @@ static const char *LookupDict2(Translator *tr, const char *word, const char *wor | |||
| wlen = strlen(word); | |||
| } | |||
| hash = HashDictionary(word); | |||
| p = tr->dict_hashtab[hash]; | |||
| @@ -3127,6 +3123,11 @@ static const char *LookupDict2(Translator *tr, const char *word, const char *wor | |||
| continue; | |||
| } | |||
| } | |||
| if(dictionary_flags & FLAG_NEEDS_DOT) | |||
| { | |||
| if(!(wflags & FLAG_HAS_DOT)) | |||
| continue; | |||
| } | |||
| if((dictionary_flags & FLAG_ATEND) && (word_end < tr->clause_end)) | |||
| { | |||
| @@ -3267,7 +3268,7 @@ int LookupDictList(Translator *tr, char **wordptr, char *ph_out, unsigned int *f | |||
| // set the skip words flag | |||
| flags[0] |= FLAG_SKIPWORDS; | |||
| dictionary_skipwords = length; | |||
| return(flags[0]); | |||
| return(1); | |||
| } | |||
| } | |||
| @@ -3367,7 +3368,7 @@ int LookupDictList(Translator *tr, char **wordptr, char *ph_out, unsigned int *f | |||
| return(0); | |||
| } | |||
| return(flags[0]); | |||
| return(1); | |||
| } | |||
| ph_out[0] = 0; | |||
| @@ -3384,6 +3385,17 @@ int Lookup(Translator *tr, const char *word, char *ph_out) | |||
| return(LookupDictList(tr, &word1, ph_out, flags, 0, NULL)); | |||
| } | |||
| int LookupFlags(Translator *tr, const char *word) | |||
| {//============================================== | |||
| char buf[100]; | |||
| static unsigned int flags[2]; | |||
| flags[0] = flags[1] = 0; | |||
| char *word1 = (char *)word; | |||
| LookupDictList(tr, &word1, buf, flags, 0, NULL); | |||
| return(flags[0]); | |||
| } | |||
| int RemoveEnding(Translator *tr, char *word, int end_type, char *word_copy) | |||
| @@ -3410,7 +3422,8 @@ int RemoveEnding(Translator *tr, char *word, int end_type, char *word_copy) | |||
| "ion", NULL }; | |||
| static const char *add_e_additions[] = { | |||
| "c", "rs", "ir", "ur", "ath", "ns", "lu", NULL }; | |||
| // "c", "rs", "ir", "ur", "ath", "ns", "lu", NULL }; | |||
| "c", "rs", "ir", "ur", "ath", "ns", "u", NULL }; | |||
| for(word_end = word; *word_end != ' '; word_end++) | |||
| { | |||
+ 2
- 1
src/espeakedit.cpp
View File
| @@ -266,6 +266,7 @@ wxSashLayoutWindow *win; | |||
| ConfigInit(); | |||
| LoadConfig(); | |||
| WavegenInitSound(); | |||
| if((result = LoadPhData()) != 1) | |||
| @@ -320,7 +321,7 @@ void MyFrame::SetVoiceTitle(char *voice_name) | |||
| { | |||
| sprintf(buf,"Compile &dictionary '%s'",dictionary_name); | |||
| data_menu->SetLabel(MENU_COMPILE_DICT, wxString(buf,wxConvLocal)); | |||
| sprintf(buf,"&Format '%s_rules' file",dictionary_name); | |||
| sprintf(buf,"&Layout '%s_rules' file",dictionary_name); | |||
| data_menu->SetLabel(MENU_FORMAT_DICTIONARY, wxString(buf,wxConvLocal)); | |||
| } | |||
| } | |||
+ 3
- 3
src/intonation.cpp
View File
| @@ -214,7 +214,7 @@ static int drops_0[8] = {0x400,0x400,0x700,0x700,0x700,0xa00,0x1800,0x0e00}; | |||
| //static int drops_2[8] = {0x400,0x400,0x600,0x600,-0x800,0xc00,0x0e00,0x0e00}; | |||
| static short oflow[] = {0, 20, 12, 4, 0}; | |||
| static short oflow_emf[] = {5, 24, 15, 10, 5}; | |||
| static short oflow_emf[] = {5, 26, 16, 10, 5}; | |||
| static short oflow_less[] = {3, 19, 12, 7, 2}; | |||
| // static short oflow_test2[] = {20, 0, 20, 0, 20}; | |||
| // static short back_emf[] = {35, 32, 0}; | |||
| @@ -262,7 +262,7 @@ static TONE_HEAD tone_head_table[N_TONE_HEAD_TABLE] = { | |||
| {20, 25, 34, 22, drops_0, 3, 3, 5, oflow}, // 0 statement | |||
| {20, 25, 34, 20, drops_0, 3, 3, 5, oflow}, // 1 comma | |||
| {20, 25, 34, 20, drops_0, 3, 3, 5, oflow}, // 2 question | |||
| {20, 25, 36, 22, drops_0, 3, 4, 5, oflow_emf}, // 3 exclamation | |||
| {20, 25, 39, 22, drops_0, 3, 4, 5, oflow_emf}, // 3 exclamation | |||
| {20, 25, 34, 22, drops_0, 3, 3, 5, oflow}, // 4 statement, emphatic | |||
| {20, 25, 32, 24, drops_0, 4, 3, 5, oflow_less}, // 5 statement, less intonation | |||
| {20, 25, 32, 24, drops_0, 4, 3, 5, oflow_less}, // 6 comma, less intonation | |||
| @@ -275,7 +275,7 @@ static TONE_HEAD tone_head_table[N_TONE_HEAD_TABLE] = { | |||
| }; | |||
| static TONE_NUCLEUS tone_nucleus_table[N_TONE_NUCLEUS_TABLE] = { | |||
| {PITCHfall, 29, 4, PITCHfall, 32, 9, NULL, 12, 6, 0}, // 0 statement | |||
| {PITCHfall, 29, 4, PITCHfall, 31, 8, NULL, 11, 6, 0}, // 0 statement | |||
| {PITCHfrise, 35, 8, PITCHfrise2, 35,10, NULL, 15, 23, 0}, // 1 comma | |||
| {PITCHfrise, 39,10, PITCHfrise2, 36,10, NULL, 15, 28, 0}, // 2 question | |||
| // {PITCHfall, 41, 4, PITCHfall, 41,27, NULL, 16, 4, T_EMPH}, // 3 exclamation | |||
+ 1
- 1
src/menus.cpp
View File
| @@ -89,7 +89,7 @@ wxMenuBar *MakeMenu(int type) | |||
| data_menu->Append(MENU_COMPILE_DICT_DEBUG, _("Compile dictionary (debu&g)")); | |||
| data_menu->Append(MENU_COMPILE_MBROLA, _("Compile &mbrola phonemes list...")); | |||
| data_menu->AppendSeparator(); | |||
| data_menu->Append(MENU_FORMAT_DICTIONARY, _("&Format *_rules file")); | |||
| data_menu->Append(MENU_FORMAT_DICTIONARY, _("&Layout *_rules file")); | |||
| // OPTIONS MENU | |||
| paths_menu = new wxMenu; | |||
+ 88
- 46
src/numbers.cpp
View File
| @@ -67,6 +67,8 @@ | |||
| static int n_digit_lookup; | |||
| static char *digit_lookup; | |||
| static int speak_missing_thousands; | |||
| typedef struct { | |||
| const char *name; | |||
| @@ -589,8 +591,8 @@ void LookupLetter(Translator *tr, unsigned int letter, int next_byte, char *ph_b | |||
| int TranslateLetter(Translator *tr, char *word, char *phonemes, int control, int word_length) | |||
| {//====================================================================================== | |||
| int TranslateLetter(Translator *tr, char *word, char *phonemes, int control) | |||
| {//========================================================================= | |||
| // get pronunciation for an isolated letter | |||
| // return number of bytes used by the letter | |||
| // control 2=say-as glyphs, 3-say-as chars | |||
| @@ -755,27 +757,28 @@ void SetSpellingStress(Translator *tr, char *phonemes, int control, int n_chars) | |||
| static char ph_ordinal2[12]; | |||
| static int CheckDotOrdinal(Translator *tr, char *word, WORD_TAB *wtab, int lowercase) | |||
| {//================================================================================== | |||
| // nextupper: Next word must start with lower-case | |||
| static int CheckDotOrdinal(Translator *tr, char *word, WORD_TAB *wtab, int roman) | |||
| {//============================================================================== | |||
| int ordinal = 0; | |||
| int c2; | |||
| if((tr->langopts.numbers & NUM_ORDINAL_DOT) && (word[0] == '.')) | |||
| if((tr->langopts.numbers & NUM_ORDINAL_DOT) && ((word[0] == '.') || (wtab[0].flags & FLAG_HAS_DOT)) && !(wtab[1].flags & FLAG_NOSPACE)) | |||
| { | |||
| if((lowercase==0) || !(wtab[1].flags & FLAG_FIRST_UPPER)) | |||
| if(roman || !(wtab[1].flags & FLAG_FIRST_UPPER)) | |||
| { | |||
| utf8_in(&c2, &word[2]); | |||
| if(IsAlpha(c2)) | |||
| if((word[1] != 0) && IsAlpha(c2)) | |||
| { | |||
| // ordinal number is indicated by dot after the number | |||
| // but not if the next word starts with an upper-case letter | |||
| ordinal = 2; | |||
| word[0] = ' '; | |||
| if(tr->translator_name == L('h','u')) | |||
| if(word[0] == '.') | |||
| word[0] = ' '; | |||
| if((roman==0) && (tr->translator_name == L('h','u'))) | |||
| { | |||
| // lang=hu don't treat dot as ordinal indicator if the next word is a month name ($alt) | |||
| // lang=hu don't treat dot as ordinal indicator if the next word is a month name ($alt). It may have a suffix. | |||
| if(TranslateWord(tr, &word[2], 0, NULL) & FLAG_ALT_TRANS) | |||
| ordinal = 0; | |||
| } | |||
| @@ -799,7 +802,7 @@ int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab) | |||
| int subtract; | |||
| int repeat = 0; | |||
| int n_digits = 0; | |||
| unsigned int flags; | |||
| unsigned int flags[2]; | |||
| char ph_roman[30]; | |||
| char number_chars[N_WORD_BYTES]; | |||
| @@ -809,6 +812,7 @@ int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab) | |||
| acc = 0; | |||
| prev = 0; | |||
| subtract = 0x7fff; | |||
| ph_out[0] = 0; | |||
| if((tr->langopts.numbers & NUM_ROMAN_CAPITALS) && !(wtab[0].flags & FLAG_ALL_UPPER)) | |||
| return(0); | |||
| @@ -861,12 +865,12 @@ int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab) | |||
| if((tr->langopts.numbers & NUM_ROMAN_AFTER) == 0) | |||
| { | |||
| strcpy(ph_out,ph_roman); | |||
| p = &ph_out[strlen(ph_out)]; | |||
| p = &ph_out[strlen(ph_roman)]; | |||
| } | |||
| sprintf(number_chars," %d ",acc); | |||
| sprintf(number_chars," %d ",acc); | |||
| if(CheckDotOrdinal(tr, word, wtab, 0)) | |||
| if(CheckDotOrdinal(tr, word, wtab, 1)) | |||
| wtab[0].flags |= FLAG_ORDINAL; | |||
| if(tr->langopts.numbers & NUM_ROMAN_ORDINAL) | |||
| @@ -876,8 +880,8 @@ int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab) | |||
| wtab[0].flags |= FLAG_ORDINAL; | |||
| } | |||
| TranslateNumber(tr, &number_chars[1], p, &flags, wtab); | |||
| tr->prev_dict_flags = 0; | |||
| TranslateNumber(tr, &number_chars[2], p, flags, wtab); | |||
| if(tr->langopts.numbers & NUM_ROMAN_AFTER) | |||
| strcat(ph_out,ph_roman); | |||
| @@ -922,6 +926,7 @@ static int LookupThousands(Translator *tr, int value, int thousandplex, int thou | |||
| char string[12]; | |||
| char ph_of[12]; | |||
| char ph_thousands[40]; | |||
| char ph_buf[40]; | |||
| ph_of[0] = 0; | |||
| @@ -976,10 +981,24 @@ static int LookupThousands(Translator *tr, int value, int thousandplex, int thou | |||
| if(Lookup(tr, string, ph_thousands) == 0) | |||
| { | |||
| // repeat "thousand" if higher order names are not available | |||
| sprintf(string,"_%dM1",value); | |||
| if((found_value = Lookup(tr, string, ph_thousands)) == 0) | |||
| Lookup(tr, "_0M1", ph_thousands); | |||
| if(thousandplex > 3) | |||
| { | |||
| sprintf(string,"_0M%d", thousandplex-1); | |||
| if(Lookup(tr, string, ph_buf) == 0) | |||
| { | |||
| // say "millions" if this name is not available and neither is the next lower | |||
| Lookup(tr, "_0M2", ph_thousands); | |||
| speak_missing_thousands = 3; | |||
| } | |||
| } | |||
| if(ph_thousands[0] == 0) | |||
| { | |||
| // repeat "thousand" if higher order names are not available | |||
| sprintf(string,"_%dM1",value); | |||
| if((found_value = Lookup(tr, string, ph_thousands)) == 0) | |||
| Lookup(tr, "_0M1", ph_thousands); | |||
| speak_missing_thousands = 2; | |||
| } | |||
| } | |||
| } | |||
| } | |||
| @@ -1015,6 +1034,9 @@ static int LookupNum2(Translator *tr, int value, int control, char *ph_out) | |||
| found = 0; | |||
| ph_ordinal[0] = 0; | |||
| ph_tens[0] = 0; | |||
| ph_digits[0] = 0; | |||
| ph_and[0] = 0; | |||
| if((control & 2) && (n_digit_lookup == 2)) | |||
| { | |||
| @@ -1366,7 +1388,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| int n_digits; | |||
| int value; | |||
| unsigned int ix; | |||
| int ix; | |||
| unsigned char c; | |||
| int suppress_null = 0; | |||
| int decimal_point = 0; | |||
| @@ -1376,7 +1398,6 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| int prev_thousands = 0; | |||
| int ordinal = 0; | |||
| int this_value; | |||
| static int prev_value; | |||
| int decimal_count; | |||
| int max_decimal_count; | |||
| int decimal_mode; | |||
| @@ -1394,16 +1415,48 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| static const char str_pause[2] = {phonPAUSE_NOLINK,0}; | |||
| *flags = 0; | |||
| n_digit_lookup = 0; | |||
| buf_digit_lookup[0] = 0; | |||
| digit_lookup = buf_digit_lookup; | |||
| for(ix=0; isdigit(word[ix]); ix++) ; | |||
| n_digits = ix; | |||
| value = this_value = atoi(word); | |||
| // is there a previous thousands part (as a previous "word") ? | |||
| if((n_digits == 3) && (word[-2] == tr->langopts.thousands_sep) && isdigit(word[-3])) | |||
| { | |||
| prev_thousands = 1; | |||
| } | |||
| else | |||
| if((tr->langopts.thousands_sep == ' ') || (tr->langopts.numbers & NUM_ALLOW_SPACE)) | |||
| { | |||
| // thousands groups can be separated by spaces | |||
| if((n_digits == 3) && isdigit(word[-2])) | |||
| { | |||
| prev_thousands = 1; | |||
| } | |||
| } | |||
| if(prev_thousands == 0) | |||
| { | |||
| speak_missing_thousands = 0; | |||
| } | |||
| ph_ordinal2[0] = 0; | |||
| ph_zeros[0] = 0; | |||
| ordinal = CheckDotOrdinal(tr, &word[ix], wtab, 1); | |||
| if(prev_thousands || (word[0] != '0')) | |||
| { | |||
| // don't check for ordinal if the number has a leading zero | |||
| ordinal = CheckDotOrdinal(tr, &word[ix], wtab, 0); | |||
| } | |||
| if((word[ix] == '.') && !isdigit(word[ix+1]) && !isdigit(word[ix+2]) && !(wtab[1].flags & FLAG_NOSPACE)) | |||
| { | |||
| // remove dot unless followed by another number | |||
| word[ix] = 0; | |||
| } | |||
| if(ordinal == 0) | |||
| { | |||
| @@ -1417,7 +1470,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| hyphen = 1; | |||
| ix++; | |||
| } | |||
| while((word[ix] != 0) && (word[ix] != ' ') && (ix < (sizeof(suffix)-1))) | |||
| while((word[ix] != 0) && (word[ix] != ' ') && (ix < int(sizeof(suffix)-1))) | |||
| { | |||
| *p++ = word[ix++]; | |||
| } | |||
| @@ -1442,20 +1495,6 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| ph_append[0] = 0; | |||
| ph_buf2[0] = 0; | |||
| // is there a previous thousands part (as a previous "word") ? | |||
| if((n_digits == 3) && (word[-2] == tr->langopts.thousands_sep) && isdigit(word[-3])) | |||
| { | |||
| prev_thousands = 1; | |||
| } | |||
| else | |||
| if((tr->langopts.thousands_sep == ' ') || (tr->langopts.numbers & NUM_ALLOW_SPACE)) | |||
| { | |||
| // thousands groups can be separated by spaces | |||
| if((n_digits == 3) && isdigit(word[-2])) | |||
| { | |||
| prev_thousands = 1; | |||
| } | |||
| } | |||
| if((word[0] == '0') && (prev_thousands == 0) && (word[1] != ' ') && (word[1] != tr->langopts.decimal_sep)) | |||
| { | |||
| @@ -1532,12 +1571,13 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| } | |||
| } | |||
| else | |||
| if((thousandplex > 1) && prev_thousands && (prev_value > 0)) | |||
| if(speak_missing_thousands == 1) | |||
| { | |||
| sprintf(string,"_%s%d",M_Variant(value),thousandplex+1); | |||
| // speak this thousandplex if there was no word for the previous thousandplex | |||
| sprintf(string,"_0M%d",thousandplex+1); | |||
| if(Lookup(tr, string, buf1)==0) | |||
| { | |||
| // speak this thousandplex if there was no word for the previous thousandplex | |||
| sprintf(string,"_0M%d",thousandplex); | |||
| Lookup(tr, string, ph_append); | |||
| } | |||
| @@ -1548,8 +1588,6 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| Lookup(tr, "_.", ph_append); | |||
| } | |||
| n_digit_lookup = 0; | |||
| buf_digit_lookup[0] = 0; | |||
| if(thousandplex == 0) | |||
| { | |||
| char *p2; | |||
| @@ -1560,13 +1598,17 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| { | |||
| p2 = p - 1; | |||
| if(LookupDictList(tr, &p2, buf_digit_lookup, flags, FLAG_SUFX, wtab)) // lookup 2 digits | |||
| { | |||
| n_digit_lookup = 2; | |||
| } | |||
| } | |||
| if((buf_digit_lookup[0] == 0) && (*p != '0')) | |||
| { | |||
| // not found, lookup only the last digit | |||
| if(LookupDictList(tr, &p, buf_digit_lookup, flags, FLAG_SUFX, wtab)) // don't match '0', or entries with $only | |||
| n_digit_lookup = 1; | |||
| { | |||
| n_digit_lookup = 1; | |||
| } | |||
| } | |||
| } | |||
| @@ -1674,7 +1716,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned | |||
| } | |||
| *flags |= FLAG_FOUND; | |||
| prev_value = this_value; | |||
| speak_missing_thousands--; | |||
| return(1); | |||
| } // end of TranslateNumber_1 | |||
+ 1
- 0
src/phoneme.h
View File
| @@ -95,6 +95,7 @@ extern const unsigned char pause_phonemes[8]; // 0, vshort, short, pause, long, | |||
| // place of articulation | |||
| #define phPLACE 0xf0000 | |||
| #define phPLACE_blb 0x10000 | |||
| #define phPLACE_pla 0x60000 | |||
| #define N_PHONEME_TABS 100 // number of phoneme tables | |||
+ 99
- 4
src/readclause.cpp
View File
| @@ -61,6 +61,7 @@ static int ignore_text=0; // set during <sub> ... </sub> to ignore text which | |||
| static int clear_skipping_text = 0; // next clause should clear the skipping_text flag | |||
| int count_characters = 0; | |||
| static int sayas_mode; | |||
| static int sayas_start; | |||
| static int ssml_ignore_l_angle = 0; | |||
| // alter tone for announce punctuation or capitals | |||
| @@ -1521,6 +1522,31 @@ static void SetProsodyParameter(int param_type, wchar_t *attr1, PARAM_STACK *sp) | |||
| } // end of SetProsodyParemeter | |||
| static int ReplaceKeyName(char *outbuf, int index, int &outix) | |||
| {//=========================================================== | |||
| // Replace some key-names by single characters, so they can be pronounced in different languages | |||
| MNEM_TAB keynames[] = { | |||
| {"space ",0xe020}, | |||
| {"tab ", 0xe009}, | |||
| {"underscore ", 0xe05f}, | |||
| {"double-quote ", '"'}, | |||
| {NULL, 0}}; | |||
| int ix; | |||
| int letter; | |||
| char *p; | |||
| p = &outbuf[index+1]; | |||
| if((letter = LookupMnem(keynames, p)) != 0) | |||
| { | |||
| ix = utf8_out(letter, p); | |||
| outix = index + ix + 1; | |||
| return(letter); | |||
| } | |||
| return(0); | |||
| } | |||
| static int ProcessSsmlTag(wchar_t *xml_buf, char *outbuf, int &outix, int n_outbuf, int self_closing) | |||
| {//================================================================================================== | |||
| @@ -1706,10 +1732,17 @@ static int ProcessSsmlTag(wchar_t *xml_buf, char *outbuf, int &outix, int n_outb | |||
| strcpy(&outbuf[outix],buf); | |||
| outix += strlen(buf); | |||
| sayas_start = outix; | |||
| sayas_mode = value; // punctuation doesn't end clause during SAY-AS | |||
| break; | |||
| case SSML_SAYAS + SSML_CLOSE: | |||
| if(sayas_mode == SAYAS_KEY) | |||
| { | |||
| outbuf[outix] = 0; | |||
| ReplaceKeyName(outbuf, sayas_start, outix); | |||
| } | |||
| outbuf[outix++] = CTRL_EMBEDDED; | |||
| outbuf[outix++] = 'Y'; | |||
| sayas_mode = 0; | |||
| @@ -1971,6 +2004,8 @@ int ReadClause(Translator *tr, FILE *f_in, char *buf, short *charix, int *charix | |||
| int is_end_clause; | |||
| int announced_punctuation; | |||
| int stressed_word = 0; | |||
| int end_clause_after_tag = 0; | |||
| int end_clause_index = 0; | |||
| const char *p; | |||
| wchar_t xml_buf[N_XML_BUF+1]; | |||
| @@ -1985,6 +2020,7 @@ int ReadClause(Translator *tr, FILE *f_in, char *buf, short *charix, int *charix | |||
| clear_skipping_text = 0; | |||
| } | |||
| tr->phonemes_repeat_count = 0; | |||
| tr->clause_upper_count = 0; | |||
| tr->clause_lower_count = 0; | |||
| end_of_input = 0; | |||
| @@ -2150,6 +2186,9 @@ f_input = f_in; // for GetC etc | |||
| if(terminator != 0) | |||
| { | |||
| if(end_clause_after_tag) | |||
| ix = end_clause_index; | |||
| buf[ix] = ' '; | |||
| buf[ix++] = 0; | |||
| @@ -2333,6 +2372,9 @@ f_input = f_in; // for GetC etc | |||
| // 2nd newline, assume paragraph | |||
| UngetC(c2); | |||
| if(end_clause_after_tag) | |||
| ix = end_clause_index; // delete clause-end punctiation | |||
| buf[ix] = ' '; | |||
| buf[ix+1] = 0; | |||
| if(parag > 3) | |||
| @@ -2359,6 +2401,30 @@ if(option_ssml) parag=1; | |||
| { | |||
| is_end_clause = 0; | |||
| if(end_clause_after_tag) | |||
| { | |||
| // Because of an xml tag, we are waiting for the | |||
| // next non-blank character to decide whether to end the clause | |||
| // i.e. is dot followed by an upper-case letter? | |||
| if(c1 == '\n') | |||
| { | |||
| // end_clause_after_tag &= ~CLAUSE_DOT; | |||
| } | |||
| if(!iswspace(c1)) | |||
| { | |||
| if(iswdigit(c1) || (IsAlpha(c1) && !iswlower(c1))) | |||
| { | |||
| UngetC(c2); | |||
| ungot_char2 = c1; | |||
| buf[end_clause_index] = ' '; // delete the end-clause punctuation | |||
| buf[end_clause_index+1] = 0; | |||
| return(end_clause_after_tag); | |||
| } | |||
| end_clause_after_tag = 0; | |||
| } | |||
| } | |||
| if((c1 == '.') && (c2 == '.')) | |||
| { | |||
| while((c_next = GetC()) == '.') | |||
| @@ -2396,6 +2462,7 @@ if(option_ssml) parag=1; | |||
| // if a list of allowed punctuation has been set up, check whether the character is in it | |||
| if((option_punctuation == 1) || (wcschr(option_punctlist,c1) != NULL)) | |||
| { | |||
| tr->phonemes_repeat_count = 0; | |||
| if((terminator = AnnouncePunctuation(tr, c1, &c2, buf, &ix, is_end_clause)) >= 0) | |||
| return(terminator); | |||
| announced_punctuation = c1; | |||
| @@ -2432,6 +2499,11 @@ if(option_ssml) parag=1; | |||
| } | |||
| } | |||
| if((c1 == '.') && (nl_count < 2)) | |||
| { | |||
| punct_data |= CLAUSE_DOT; | |||
| } | |||
| if(nl_count==0) | |||
| { | |||
| if(c1 == '.') | |||
| @@ -2440,14 +2512,21 @@ if(option_ssml) parag=1; | |||
| (iswdigit(cprev) || (IsRomanU(cprev) && (IsRomanU(cprev2) || iswspace(cprev2))))) // lang=hu | |||
| { | |||
| // dot after a number indicates an ordinal number | |||
| if(!iswdigit(cprev) || iswlower(c_next) || (c_next == '<')) | |||
| is_end_clause = 0; // only if followed by lower-case, (or if there is a XML tag) | |||
| if(!iswdigit(cprev)) | |||
| { | |||
| is_end_clause = 0; // Roman number followed by dot | |||
| } | |||
| else | |||
| { | |||
| if (iswlower(c_next)) | |||
| is_end_clause = 0; // only if followed by lower-case, (or if there is a XML tag) | |||
| } | |||
| } | |||
| else | |||
| if(iswlower(c_next)) | |||
| { | |||
| // next word has no capital letter, this dot is probably from an abbreviation | |||
| c1 = ' '; | |||
| // c1 = ' '; | |||
| is_end_clause = 0; | |||
| } | |||
| if(any_alnum==0) | |||
| @@ -2466,6 +2545,14 @@ if(option_ssml) parag=1; | |||
| is_end_clause = 0; | |||
| } | |||
| } | |||
| if(is_end_clause && (c1 == '.') && (c_next == '<') && option_ssml) | |||
| { | |||
| // wait until after the end of the xml tag, then look for upper-case letter | |||
| is_end_clause = 0; | |||
| end_clause_index = ix; | |||
| end_clause_after_tag = punct_data; | |||
| } | |||
| } | |||
| if(is_end_clause) | |||
| @@ -2473,7 +2560,11 @@ if(option_ssml) parag=1; | |||
| UngetC(c_next); | |||
| buf[ix] = ' '; | |||
| buf[ix+1] = 0; | |||
| if(!IsAlpha(c_next)) | |||
| { | |||
| punct_data &= ~CLAUSE_DOT; | |||
| } | |||
| if(nl_count > 1) | |||
| { | |||
| if((punct_data == CLAUSE_QUESTION) || (punct_data == CLAUSE_EXCLAMATION)) | |||
| @@ -2536,6 +2627,10 @@ if(option_ssml) parag=1; | |||
| { | |||
| ix += utf8_out(CHAR_EMPHASIS, &buf[ix]); | |||
| } | |||
| if(end_clause_after_tag) | |||
| { | |||
| ix = end_clause_index; // delete clause-end punctuation | |||
| } | |||
| buf[ix] = ' '; | |||
| buf[ix+1] = 0; | |||
| return(CLAUSE_EOF); // end of file | |||
+ 2
- 2
src/setlengths.cpp
View File
| @@ -326,10 +326,10 @@ void CalcLengths(Translator *tr) | |||
| case phSTOP: | |||
| last_pitch = 0; | |||
| if(prev->type == phFRICATIVE) | |||
| p->prepause = 20; | |||
| p->prepause = 25; | |||
| else | |||
| if((more_syllables > 0) || (stress < 4)) | |||
| p->prepause = 40; | |||
| p->prepause = 48; | |||
| else | |||
| p->prepause = 60; | |||
+ 39
- 1
src/speak_lib.cpp
View File
| @@ -47,6 +47,7 @@ | |||
| #include "wave.h" | |||
| unsigned char *outbuf=NULL; | |||
| extern FILE *f_logespeak; | |||
| extern espeak_VOICE voice_selected; | |||
| espeak_EVENT *event_list=NULL; | |||
| @@ -713,7 +714,12 @@ ENTER("espeak_Initialize"); | |||
| init_path(path); | |||
| initialise(); | |||
| select_output(output_type); | |||
| if(f_logespeak) | |||
| { | |||
| fprintf(f_logespeak,"INIT mode %d options 0x%x\n",output_type,options); | |||
| } | |||
| // buflength is in mS, allocate 2 bytes per sample | |||
| if(buf_length == 0) | |||
| buf_length = 200; | |||
| @@ -763,6 +769,12 @@ ESPEAK_API espeak_ERROR espeak_Synth(const void *text, size_t size, | |||
| SHOW("espeak_Synth > position=%d, position_type=%d, end_position=%d, flags=%d, user_data=0x%x, text=%s\n", position, position_type, end_position, flags, user_data, text); | |||
| #endif | |||
| if(f_logespeak) | |||
| { | |||
| fprintf(f_logespeak,"\nSYNTH posn %d %d %d flags 0x%x\n%s\n",position,end_position,position_type,flags, (const char *)text); | |||
| fflush(f_logespeak); | |||
| } | |||
| espeak_ERROR a_error=EE_INTERNAL_ERROR; | |||
| static unsigned int temp_identifier; | |||
| @@ -825,6 +837,12 @@ ESPEAK_API espeak_ERROR espeak_Synth_Mark(const void *text, size_t size, | |||
| espeak_ERROR a_error=EE_OK; | |||
| static unsigned int temp_identifier; | |||
| if(f_logespeak) | |||
| { | |||
| fprintf(f_logespeak,"\nSYNTH MARK %s posn %d flags 0x%x\n%s\n",index_mark,end_position,flags, (const char *)text); | |||
| } | |||
| if (unique_identifier == NULL) | |||
| { | |||
| unique_identifier = &temp_identifier; | |||
| @@ -875,6 +893,11 @@ ESPEAK_API espeak_ERROR espeak_Key(const char *key) | |||
| ENTER("espeak_Key"); | |||
| // symbolic name, symbolicname_character - is there a system resource of symbolicnames per language | |||
| if(f_logespeak) | |||
| { | |||
| fprintf(f_logespeak,"\nKEY %s\n",key); | |||
| } | |||
| espeak_ERROR a_error = EE_OK; | |||
| if(synchronous_mode) | |||
| @@ -901,6 +924,11 @@ ESPEAK_API espeak_ERROR espeak_Char(wchar_t character) | |||
| ENTER("espeak_Char"); | |||
| // is there a system resource of character names per language? | |||
| if(f_logespeak) | |||
| { | |||
| fprintf(f_logespeak,"\nCHAR U+%x\n",character); | |||
| } | |||
| #ifdef USE_ASYNC | |||
| espeak_ERROR a_error; | |||
| @@ -997,6 +1025,10 @@ ESPEAK_API espeak_ERROR espeak_SetParameter(espeak_PARAMETER parameter, int valu | |||
| {//============================================================================================= | |||
| ENTER("espeak_SetParameter"); | |||
| if(f_logespeak) | |||
| { | |||
| fprintf(f_logespeak,"SETPARAM %d %d %d\n",parameter,value,relative); | |||
| } | |||
| #ifdef USE_ASYNC | |||
| espeak_ERROR a_error; | |||
| @@ -1141,6 +1173,12 @@ ESPEAK_API espeak_ERROR espeak_Terminate(void) | |||
| outbuf = NULL; | |||
| FreePhData(); | |||
| if(f_logespeak) | |||
| { | |||
| fclose(f_logespeak); | |||
| f_logespeak = NULL; | |||
| } | |||
| return EE_OK; | |||
| } // end of espeak_Terminate | |||
+ 1
- 1
src/speak_lib.h
View File
| @@ -507,7 +507,7 @@ const espeak_VOICE **espeak_ListVoices(espeak_VOICE *voice_spec); | |||
| The list is terminated by a NULL pointer | |||
| If voice_spec is NULL then all voices are listed. | |||
| If voice spec is give, then only the voices which are compatible with the voice_spec | |||
| If voice spec is given, then only the voices which are compatible with the voice_spec | |||
| are listed, and they are listed in preference order. | |||
| */ | |||
+ 14
- 2
src/synthdata.cpp
View File
| @@ -35,10 +35,12 @@ | |||
| #include "translate.h" | |||
| #include "wave.h" | |||
| const char *version_string = "1.41.32 09.Nov.09"; | |||
| const int version_phdata = 0x014118; | |||
| const char *version_string = "1.42.02 30.Nov.09"; | |||
| const int version_phdata = 0x014200; | |||
| int option_device_number = -1; | |||
| FILE *f_logespeak = NULL; | |||
| int logging_type; | |||
| // copy the current phoneme table into here | |||
| int n_phoneme_tab; | |||
| @@ -640,6 +642,8 @@ void LoadConfig(void) | |||
| char *p; | |||
| char string[200]; | |||
| logging_type = 0; | |||
| for(ix=0; ix<N_SOUNDICON_SLOTS; ix++) | |||
| { | |||
| soundicon_tab[ix].filename = NULL; | |||
| @@ -654,6 +658,14 @@ void LoadConfig(void) | |||
| while(fgets(buf,sizeof(buf),f)!=NULL) | |||
| { | |||
| if(buf[0] == '/') continue; | |||
| if(memcmp(buf,"log",3)==0) | |||
| { | |||
| if(sscanf(&buf[4],"%d %s",&logging_type,string)==2) | |||
| f_logespeak = fopen(string,"w"); | |||
| } | |||
| else | |||
| if(memcmp(buf,"tone",4)==0) | |||
| { | |||
| ReadTonePoints(&buf[5],tone_points); | |||
+ 51
- 12
src/synthesize.cpp
View File
| @@ -876,36 +876,65 @@ int DoSpect(PHONEME_TAB *this_ph, PHONEME_TAB *prev_ph, PHONEME_TAB *next_ph, | |||
| int ix; | |||
| long *q; | |||
| int len; | |||
| int min; | |||
| int match_level; | |||
| int frame_length; | |||
| int frame1_length; | |||
| int frame2_length; | |||
| int length_factor; | |||
| int length_mod; | |||
| int length_mod2; // reduced effect length_mod | |||
| int total_len = 0; | |||
| int len_adjust_factor = 256; | |||
| static int wave_flag = 0; | |||
| int wcmd_spect = WCMD_SPECT; | |||
| length_mod = plist->length; | |||
| if(length_mod==0) length_mod=256; | |||
| if(which==1) | |||
| { | |||
| // limit the shortening of sonorants before shortened (eg. unstressed vowels) | |||
| if((this_ph->type==phLIQUID) || (prev_ph->type==phLIQUID) || (prev_ph->type==phNASAL)) | |||
| length_mod2 = (length_mod*(256-speed.speed_factor3) + 256*speed.speed_factor3)/256; | |||
| if(which==1) | |||
| { | |||
| if(length_mod < (len = translator->langopts.param[LOPT_SONORANT_MIN])) | |||
| // limit the shortening of sonorants before shortened (eg. unstressed vowels) | |||
| if((this_ph->type==phLIQUID) || (prev_ph->type==phLIQUID) || (prev_ph->type==phNASAL)) | |||
| { | |||
| length_mod = len; | |||
| if(length_mod < (len = translator->langopts.param[LOPT_SONORANT_MIN])) | |||
| { | |||
| length_mod = len; | |||
| } | |||
| } | |||
| } | |||
| } | |||
| modn_flags = 0; | |||
| frames = LookupSpect(this_ph,prev_ph,next_ph,which,&match_level,&n_frames, plist); | |||
| if(frames == NULL) | |||
| return(0); // not found | |||
| // if((which==2) && (this_ph->phflags & phLONG)) | |||
| if((which==2) && (this_ph->std_length >= 200)) | |||
| { | |||
| // apply a minimum length for long vowels at fast speeds, to keep the distinction with short vowels | |||
| total_len = 0; | |||
| for(frameix=0; frameix<(n_frames-1); frameix++) | |||
| { | |||
| length_factor = length_mod; | |||
| if(frames[frameix].frflags & FRFLAG_LEN_MOD) // reduce effect of length mod | |||
| { | |||
| length_factor = length_mod2; | |||
| } | |||
| len = (frames[frameix].length * samplerate)/1000; | |||
| len = (len * length_factor)/256; | |||
| total_len += len; | |||
| } | |||
| min = translator->langopts.param[LOPT_MIN_LONG_VOWEL] * (samplerate)/1000; | |||
| min = (min * length_mod2)/256; | |||
| if(total_len < min) | |||
| { | |||
| len_adjust_factor = (min*256)/total_len; | |||
| } | |||
| } | |||
| frame1 = frames[0].frame; | |||
| frame1_length = frames[0].length; | |||
| if(voice->klattv[0]) | |||
| @@ -960,6 +989,7 @@ if(which==1) | |||
| syllable_centre = wcmdq_tail; | |||
| } | |||
| total_len = 0; | |||
| frame_length = frame1_length; | |||
| for(frameix=1; frameix<n_frames; frameix++) | |||
| { | |||
| @@ -978,10 +1008,11 @@ if(which==1) | |||
| length_factor = length_mod; | |||
| if(frame1->frflags & FRFLAG_LEN_MOD) // reduce effect of length mod | |||
| { | |||
| length_factor = (length_mod*(256-speed.speed_factor3) + 256*speed.speed_factor3)/256; | |||
| length_factor = length_mod2; | |||
| } | |||
| len = (frame_length * samplerate)/1000; | |||
| len = (len * length_factor)/256; | |||
| len = (len * len_adjust_factor)/256; | |||
| if(modulation >= 0) | |||
| { | |||
| @@ -1210,8 +1241,16 @@ int Generate(PHONEME_LIST *phoneme_list, int *n_ph, int resume) | |||
| case phSTOP: | |||
| released = 0; | |||
| if(next->type==phVOWEL) released = 1; | |||
| if(next->type==phLIQUID && !next->newword) released = 1; | |||
| if(next->type==phVOWEL) | |||
| { | |||
| released = 1; | |||
| } | |||
| else | |||
| if(!next->newword) | |||
| { | |||
| if(next->type==phLIQUID) released = 1; | |||
| // if(((p->ph->phflags & phPLACE) == phPLACE_blb) && (next->ph->phflags & phSIBILANT)) released = 1; | |||
| } | |||
| if(released) | |||
| DoSample(p->ph,next->ph,2,0,0); | |||
| @@ -1307,7 +1346,7 @@ int Generate(PHONEME_LIST *phoneme_list, int *n_ph, int resume) | |||
| } | |||
| } | |||
| if((next->type==phVOWEL) || ((next->type==phLIQUID)) && (next->newword==0)) // ?? test 14.Aug.2007 | |||
| if((next->type==phVOWEL) || ((next->type==phLIQUID) && (next->newword==0))) // ?? test 14.Aug.2007 | |||
| { | |||
| StartSyllable(); | |||
| if(p->synthflags & SFLAG_LENGTHEN) | |||
+ 28
- 13
src/tr_languages.cpp
View File
| @@ -46,6 +46,7 @@ | |||
| #define OFFSET_GREEK 0x380 | |||
| #define OFFSET_CYRILLIC 0x420 | |||
| #define OFFSET_ARMENIAN 0x530 | |||
| #define OFFSET_ARABIC 0x600 | |||
| #define OFFSET_DEVANAGARI 0x900 | |||
| #define OFFSET_BENGALI 0x980 | |||
| #define OFFSET_GURMUKHI 0xa00 | |||
| @@ -156,6 +157,7 @@ static Translator* NewTranslator(void) | |||
| tr->langopts.param[LOPT_UNPRONOUNCABLE] = 's'; // don't count this character at start of word | |||
| tr->langopts.param[LOPT_BRACKET_PAUSE] = 4; // pause at bracket | |||
| tr->langopts.param2[LOPT_BRACKET_PAUSE] = 2; // pauses when announcing bracket names | |||
| tr->langopts.param[LOPT_MIN_LONG_VOWEL] = 40; | |||
| tr->langopts.max_initial_consonants = 3; | |||
| tr->langopts.replace_chars = NULL; | |||
| tr->langopts.ascii_language = ""; // Non-Latin alphabet languages, use this language to speak Latin words, default is English | |||
| @@ -221,7 +223,9 @@ void SetIndicLetters(Translator *tr) | |||
| static const char dev_consonants2[] = {0x02,0x03,0x58,0x59,0x5a,0x5b,0x5c,0x5d,0x5e,0x5f}; | |||
| memset(tr->letter_bits,0,sizeof(tr->letter_bits)); | |||
| SetLetterBitsRange(tr,LETTERGP_A,0x04,0x14); // vowel letters only | |||
| SetLetterBitsRange(tr,LETTERGP_A,0x04,0x14); // vowel letters | |||
| SetLetterBitsRange(tr,LETTERGP_A,0x3e,0x4d); // + vowel signs, and virama | |||
| SetLetterBitsRange(tr,LETTERGP_B,0x3e,0x4d); // vowel signs, and virama | |||
| SetLetterBitsRange(tr,LETTERGP_C,0x15,0x39); // the main consonant range | |||
| @@ -274,6 +278,12 @@ Translator *SelectTranslator(const char *name) | |||
| } | |||
| break; | |||
| case L('a','r'): // Arabic | |||
| case L('u','r'): // Urdu | |||
| tr->letter_bits_offset = OFFSET_ARABIC; | |||
| tr->langopts.param[LOPT_UNPRONOUNCABLE] = 1; // disable check for unpronouncable words | |||
| break; | |||
| case L('b','n'): // Bengali | |||
| { | |||
| static const short stress_lengths_bn[8] = {180, 180, 210, 210, 0, 0, 230, 240}; | |||
| @@ -463,13 +473,15 @@ Translator *SelectTranslator(const char *name) | |||
| static const unsigned char stress_amps_eu[8] = {16,16, 18,18, 18,18, 18,18 }; | |||
| SetupTranslator(tr,stress_lengths_eu,stress_amps_eu); | |||
| tr->langopts.stress_rule = STRESSPOSN_2L; // ?? second syllable ?? | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS + NUM_DECIMAL_COMMA | NUM_AND_UNITS | NUM_HUNDRED_AND | NUM_OMIT_1_HUNDRED | NUM_VIGESIMAL; | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS | NUM_DECIMAL_COMMA | NUM_AND_UNITS | NUM_HUNDRED_AND | NUM_OMIT_1_HUNDRED | NUM_VIGESIMAL; | |||
| } | |||
| break; | |||
| case L('f','a'): // Farsi | |||
| { | |||
| tr->letter_bits_offset = OFFSET_ARABIC; | |||
| tr->langopts.numbers = NUM_AND_UNITS | NUM_HUNDRED_AND; | |||
| tr->langopts.param[LOPT_UNPRONOUNCABLE] = 1; // disable check for unpronouncable words | |||
| } | |||
| break; | |||
| @@ -486,6 +498,7 @@ Translator *SelectTranslator(const char *name) | |||
| tr->langopts.stress_flags = 0x56; // move secondary stress from light to a following heavy syllable | |||
| tr->langopts.param[LOPT_IT_DOUBLING] = 1; | |||
| tr->langopts.long_stop = 130; | |||
| tr->langopts.param[LOPT_MIN_LONG_VOWEL] = 65; | |||
| tr->langopts.numbers = NUM_DECIMAL_COMMA + NUM_ALLOW_SPACE; | |||
| SetLetterVowel(tr,'y'); | |||
| @@ -506,7 +519,7 @@ Translator *SelectTranslator(const char *name) | |||
| tr->langopts.stress_flags = 0x0024; // don't use secondary stress | |||
| tr->langopts.param[LOPT_IT_LENGTHEN] = 1; // remove lengthen indicator from unstressed syllables | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS + NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_OMIT_1_HUNDRED | NUM_NOPAUSE | NUM_ROMAN | NUM_VIGESIMAL | NUM_DFRACTION_4; | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS | NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_OMIT_1_HUNDRED | NUM_NOPAUSE | NUM_ROMAN | NUM_VIGESIMAL | NUM_DFRACTION_4; | |||
| SetLetterVowel(tr,'y'); | |||
| } | |||
| break; | |||
| @@ -558,7 +571,7 @@ Translator *SelectTranslator(const char *name) | |||
| tr->langopts.spelling_stress = 1; | |||
| tr->langopts.accents = 1; | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS + NUM_HUNDRED_AND | NUM_DECIMAL_COMMA | NUM_THOUS_SPACE | NUM_DFRACTION_2 | NUM_ROMAN_UC; | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS | NUM_HUNDRED_AND | NUM_OMIT_1_HUNDRED | NUM_DECIMAL_COMMA | NUM_THOUS_SPACE | NUM_DFRACTION_2 | NUM_ROMAN_UC; | |||
| tr->langopts.numbers2 = 0x4a; // variant numbers before thousands,milliards | |||
| tr->langopts.replace_chars = replace_cyrillic_latin; | |||
| @@ -578,11 +591,11 @@ Translator *SelectTranslator(const char *name) | |||
| tr->langopts.vowel_pause = 0x20; | |||
| tr->langopts.stress_rule = STRESSPOSN_1L; | |||
| tr->langopts.stress_flags = 0x8036 | STRS_HYPEN_UNSTRESS; | |||
| tr->langopts.stress_flags = 0x8036 | S_HYPEN_UNSTRESS; | |||
| tr->langopts.unstressed_wd1 = 2; | |||
| tr->langopts.param[LOPT_IT_DOUBLING] = 1; | |||
| tr->langopts.param[LOPT_ANNOUNCE_PUNCT] = 2; // don't break clause before announcing . ? ! | |||
| // tr->langopts.param[LOPT_COMBINE_WORDS] = 9; // combine some prepositions with the following word | |||
| tr->langopts.param[LOPT_MIN_LONG_VOWEL] = 65; | |||
| tr->langopts.numbers = NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_DFRACTION_5 | NUM_ROMAN | NUM_ROMAN_ORDINAL | NUM_ROMAN_CAPITALS | NUM_ORDINAL_DOT | NUM_OMIT_1_HUNDRED; | |||
| tr->langopts.min_roman = 1; | |||
| @@ -786,7 +799,7 @@ SetLengthMods(tr,3); // all equal | |||
| SetupTranslator(tr,stress_lengths_no,NULL); | |||
| tr->langopts.stress_rule = STRESSPOSN_1L; | |||
| SetLetterVowel(tr,'y'); | |||
| tr->langopts.numbers = NUM_DECIMAL_COMMA | NUM_HUNDRED_AND | NUM_ALLOW_SPACE | NUM_1900 + NUM_ORDINAL_DOT; | |||
| tr->langopts.numbers = NUM_DECIMAL_COMMA | NUM_HUNDRED_AND | NUM_ALLOW_SPACE | NUM_1900 | NUM_ORDINAL_DOT; | |||
| } | |||
| break; | |||
| @@ -822,18 +835,19 @@ SetLengthMods(tr,3); // all equal | |||
| case L('p','t'): // Portuguese | |||
| { | |||
| static const short stress_lengths_pt[8] = {180, 125, 210, 210, 0, 0, 270, 295}; | |||
| static const unsigned char stress_amps_pt[8] = {16,13, 19,19, 20,22, 22,21 }; // 'diminished' is used to mark a quieter, final unstressed syllable | |||
| static const short stress_lengths_pt[8] = {170, 115, 210, 240, 0, 0, 260, 280}; | |||
| static const unsigned char stress_amps_pt[8] = {16,11, 19,21, 20,22, 22,21 }; // 'diminished' is used to mark a quieter, final unstressed syllable | |||
| SetupTranslator(tr,stress_lengths_pt,stress_amps_pt); | |||
| tr->langopts.length_mods0 = tr->langopts.length_mods; // don't lengthen vowels in the last syllable | |||
| tr->langopts.stress_rule = STRESSPOSN_1R; // stress on final syllable | |||
| tr->langopts.stress_flags = 0x6 | 0x10 | 0x20000; | |||
| tr->langopts.stress_flags = 0x6 | 0x10 | 0x2000 | 0x20000; | |||
| tr->langopts.numbers = NUM_DECIMAL_COMMA | NUM_DFRACTION_2 | NUM_HUNDRED_AND | NUM_AND_UNITS | NUM_ROMAN; | |||
| SetLetterVowel(tr,'y'); | |||
| ResetLetterBits(tr,0x2); | |||
| SetLetterBits(tr,1,"bcdfgjkmnpqstvxz"); // B hard consonants, excluding h,l,r,w,y | |||
| tr->langopts.param[LOPT_ALT] = 2; // call ApplySpecialAttributes2() if a word has $alt or $alt2 | |||
| } | |||
| break; | |||
| @@ -924,7 +938,7 @@ SetLengthMods(tr,3); // all equal | |||
| tr->langopts.stress_rule = STRESSPOSN_1L; | |||
| SetLetterVowel(tr,'y'); | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS + NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_1900; | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS | NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_1900; | |||
| tr->langopts.accents = 1; | |||
| } | |||
| break; | |||
| @@ -959,7 +973,7 @@ SetLengthMods(tr,3); // all equal | |||
| tr->langopts.stress_rule = STRESSPOSN_1L; | |||
| tr->langopts.stress_flags = 0x10004; // use 'diminished' for unstressed final syllable | |||
| tr->langopts.break_numbers = 0x24a8; // 1000, 100,000 10,000,000 | |||
| tr->langopts.break_numbers = 0x14a8; // 1000, 100,000 10,000,000 | |||
| if(name2 == L('t','a')) | |||
| { | |||
| @@ -1015,7 +1029,7 @@ SetLengthMods(tr,3); // all equal | |||
| tr->langopts.stress_rule = 7; // stress on the last syllable, before any explicitly unstressed syllable | |||
| tr->langopts.stress_flags = 0x20; //no automatic secondary stress | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS + NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_OMIT_1_HUNDRED | NUM_DFRACTION_2; | |||
| tr->langopts.numbers = NUM_SINGLE_STRESS | NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_OMIT_1_HUNDRED | NUM_DFRACTION_2; | |||
| tr->langopts.max_initial_consonants = 2; | |||
| } | |||
| break; | |||
| @@ -1093,6 +1107,7 @@ SetLengthMods(tr,3); // all equal | |||
| { | |||
| tr->langopts.thousands_sep = 0; // don't allow thousands separator, except space | |||
| } | |||
| return(tr); | |||
| } // end of SelectTranslator | |||
+ 96
- 45
src/translate.cpp
View File
| @@ -80,7 +80,11 @@ int pre_pause; | |||
| // these were previously in translator class | |||
| #ifdef PLATFORM_WINDOWS | |||
| char word_phonemes[N_WORD_PHONEMES*2]; // longer, because snprint() is not available | |||
| #else | |||
| char word_phonemes[N_WORD_PHONEMES]; // a word translated into phoneme codes | |||
| #endif | |||
| int n_ph_list2; | |||
| PHONEME_LIST2 ph_list2[N_PHONEME_LIST]; // first stage of text->phonemes | |||
| @@ -384,6 +388,9 @@ int IsAlpha(unsigned int c) | |||
| return(0); | |||
| } | |||
| if((c >= 0x64b) && (c <= 0x65e)) | |||
| return(1); // arabic vowel marks | |||
| if((c >= 0x300) && (c <= 0x36f)) | |||
| return(1); // combining accents | |||
| @@ -567,7 +574,6 @@ char *strchr_w(const char *s, int c) | |||
| int TranslateWord(Translator *tr, char *word1, int next_pause, WORD_TAB *wtab) | |||
| {//=========================================================================== | |||
| // word1 is terminated by space (0x20) character | |||
| @@ -585,17 +591,16 @@ int TranslateWord(Translator *tr, char *word1, int next_pause, WORD_TAB *wtab) | |||
| char *wordx; | |||
| char phonemes[N_WORD_PHONEMES]; | |||
| char *ph_limit; | |||
| char *phonemes_ptr; | |||
| char prefix_phonemes[N_WORD_PHONEMES]; | |||
| char unpron_phonemes[N_WORD_PHONEMES]; | |||
| char end_phonemes[N_WORD_PHONEMES]; | |||
| char word_copy[N_WORD_BYTES]; | |||
| char prefix_chars[N_WORD_BYTES]; | |||
| char prefix_chars[41]; | |||
| int found=0; | |||
| int end_flags; | |||
| char c_temp; // save a character byte while we temporarily replace it with space | |||
| int first_char; | |||
| int last_char = 0; | |||
| int unpron_length; | |||
| int add_plural_suffix = 0; | |||
| int prefix_flags = 0; | |||
| int confirm_prefix; | |||
| @@ -626,6 +631,8 @@ int TranslateWord(Translator *tr, char *word1, int next_pause, WORD_TAB *wtab) | |||
| dictionary_flags2[1] = 0; | |||
| dictionary_skipwords = 0; | |||
| phonemes[0] = 0; | |||
| unpron_phonemes[0] = 0; | |||
| prefix_phonemes[0] = 0; | |||
| end_phonemes[0] = 0; | |||
| ph_limit = &phonemes[N_WORD_PHONEMES]; | |||
| @@ -649,15 +656,22 @@ int TranslateWord(Translator *tr, char *word1, int next_pause, WORD_TAB *wtab) | |||
| word_length++; | |||
| } | |||
| // try an initial lookup in the dictionary list, we may find a pronunciation specified, or | |||
| // we may just find some flags | |||
| spell_word = 0; | |||
| if(option_sayas == SAYAS_KEY) | |||
| { | |||
| if(word_length == 1) | |||
| spell_word = 4; | |||
| else | |||
| { | |||
| // is there a translation for this keyname ? | |||
| word1--; | |||
| *word1 = '_'; // prefix keyname with '_' | |||
| found = LookupDictList(tr, &word1, phonemes, dictionary_flags, 0, wtab); | |||
| } | |||
| } | |||
| // try an initial lookup in the dictionary list, we may find a pronunciation specified, or | |||
| // we may just find some flags | |||
| if(option_sayas & 0x10) | |||
| { | |||
| // SAYAS_CHAR, SAYAS_GYLPH, or SAYAS_SINGLE_CHAR | |||
| @@ -665,9 +679,10 @@ int TranslateWord(Translator *tr, char *word1, int next_pause, WORD_TAB *wtab) | |||
| } | |||
| else | |||
| { | |||
| found = LookupDictList(tr, &word1, phonemes, dictionary_flags, FLAG_ALLOW_TEXTMODE, wtab); // the original word | |||
| if(!found) | |||
| found = LookupDictList(tr, &word1, phonemes, dictionary_flags, FLAG_ALLOW_TEXTMODE, wtab); // the original word | |||
| if((dictionary_flags[0] & FLAG_DOT) && (wordx[1] == '.')) | |||
| if((dictionary_flags[0] & (FLAG_ALLOW_DOT || FLAG_NEEDS_DOT)) && (wordx[1] == '.')) | |||
| { | |||
| wordx[1] = ' '; // remove a Dot after this word | |||
| } | |||
| @@ -773,7 +788,7 @@ if((wmark > 0) && (wmark < 8)) | |||
| while(*wordx != ' ') | |||
| { | |||
| wordx += TranslateLetter(tr,wordx, phonemes,spell_word, word_length); | |||
| wordx += TranslateLetter(tr,wordx, phonemes, spell_word); | |||
| posn++; | |||
| if(phonemes[0] == phonSWITCH) | |||
| { | |||
| @@ -802,13 +817,13 @@ if((wmark > 0) && (wmark < 8)) | |||
| // This word looks "unpronouncable", so speak letters individually until we | |||
| // find a remainder that we can pronounce. | |||
| emphasize_allcaps = 0; | |||
| wordx += TranslateLetter(tr,wordx,phonemes,0, word_length); | |||
| wordx += TranslateLetter(tr, wordx, unpron_phonemes, 0); | |||
| posn++; | |||
| if(phonemes[0] == phonSWITCH) | |||
| { | |||
| // change to another language in order to translate this word | |||
| strcpy(word_phonemes,phonemes); | |||
| if(strcmp(&phonemes[1],"en")==0) | |||
| strcpy(word_phonemes,unpron_phonemes); | |||
| if(strcmp(&unpron_phonemes[1],"en")==0) | |||
| return(FLAG_SPELLWORD); // _^_en must have been set in TranslateLetter(), not *_rules | |||
| return(0); | |||
| } | |||
| @@ -828,13 +843,12 @@ if((wmark > 0) && (wmark < 8)) | |||
| if(length > 0) | |||
| wordx[-1] = ' '; // prevent this affecting the pronunciation of the pronuncable part | |||
| } | |||
| SetSpellingStress(tr,phonemes,0,posn); | |||
| SetSpellingStress(tr,unpron_phonemes,0,posn); | |||
| // anything left ? | |||
| if(*wordx != ' ') | |||
| { | |||
| // Translate the stem | |||
| unpron_length = strlen(phonemes); | |||
| end_type = TranslateRules(tr, wordx, phonemes, N_WORD_PHONEMES, end_phonemes, wflags, dictionary_flags); | |||
| if(phonemes[0] == phonSWITCH) | |||
| @@ -855,7 +869,7 @@ if((wmark > 0) && (wmark < 8)) | |||
| posn = 0; | |||
| while((*wordx != ' ') && (*wordx != 0)) | |||
| { | |||
| wordx += TranslateLetter(tr,wordx, phonemes, 4, word_length); | |||
| wordx += TranslateLetter(tr,wordx, phonemes, 4); | |||
| posn++; | |||
| if(phonemes[0] == phonSWITCH) | |||
| { | |||
| @@ -1000,14 +1014,13 @@ strcpy(phonemes2,phonemes); | |||
| // The word has a standard ending, re-translate without this ending | |||
| end_flags = RemoveEnding(tr, wordx, end_type, word_copy); | |||
| phonemes_ptr = &phonemes[unpron_length]; | |||
| phonemes_ptr[0] = 0; | |||
| phonemes[0] = 0; | |||
| if(prefix_phonemes[0] != 0) | |||
| { | |||
| // lookup the stem without the prefix removed | |||
| wordx[-1] = c_temp; | |||
| found = LookupDictList(tr, &word1, phonemes_ptr, dictionary_flags2, end_flags, wtab); // include prefix, but not suffix | |||
| found = LookupDictList(tr, &word1, phonemes, dictionary_flags2, end_flags, wtab); // include prefix, but not suffix | |||
| wordx[-1] = ' '; | |||
| if(dictionary_flags[0]==0) | |||
| { | |||
| @@ -1022,12 +1035,12 @@ strcpy(phonemes2,phonemes); | |||
| } | |||
| if(found == 0) | |||
| { | |||
| found = LookupDictList(tr, &wordx, phonemes_ptr, dictionary_flags2, end_flags, wtab); // without prefix and suffix | |||
| if(phonemes_ptr[0] == phonSWITCH) | |||
| found = LookupDictList(tr, &wordx, phonemes, dictionary_flags2, end_flags, wtab); // without prefix and suffix | |||
| if(phonemes[0] == phonSWITCH) | |||
| { | |||
| // change to another language in order to translate this word | |||
| memcpy(wordx,word_copy,strlen(word_copy)); | |||
| strcpy(word_phonemes,phonemes_ptr); | |||
| strcpy(word_phonemes,phonemes); | |||
| return(0); | |||
| } | |||
| if(dictionary_flags[0]==0) | |||
| @@ -1115,15 +1128,23 @@ strcpy(phonemes2,phonemes); | |||
| *p = phonSTRESS_3; | |||
| } | |||
| } | |||
| strcpy(word_phonemes,prefix_phonemes); | |||
| strcat(word_phonemes,phonemes); | |||
| #ifdef PLATFORM_WINDOWS | |||
| sprintf(word_phonemes, "%s%s%s", unpron_phonemes, prefix_phonemes, phonemes); | |||
| #else | |||
| snprintf(word_phonemes, sizeof(word_phonemes), "%s%s%s", unpron_phonemes, prefix_phonemes, phonemes); | |||
| #endif | |||
| word_phonemes[N_WORD_PHONEMES-1] = 0; | |||
| SetWordStress(tr, word_phonemes, dictionary_flags, -1, 0); | |||
| } | |||
| else | |||
| { | |||
| // stress position affects the whole word, including prefix | |||
| strcpy(word_phonemes,prefix_phonemes); | |||
| strcat(word_phonemes,phonemes); | |||
| #ifdef PLATFORM_WINDOWS | |||
| sprintf(word_phonemes, "%s%s%s", unpron_phonemes, prefix_phonemes, phonemes); | |||
| #else | |||
| snprintf(word_phonemes, sizeof(word_phonemes), "%s%s%s", unpron_phonemes, prefix_phonemes, phonemes); | |||
| #endif | |||
| word_phonemes[N_WORD_PHONEMES-1] = 0; | |||
| SetWordStress(tr, word_phonemes, dictionary_flags, -1, tr->prev_last_stress); | |||
| } | |||
| } | |||
| @@ -1133,14 +1154,20 @@ strcpy(phonemes2,phonemes); | |||
| SetWordStress(tr, phonemes, dictionary_flags, -1, tr->prev_last_stress); | |||
| else | |||
| SetWordStress(tr, phonemes, dictionary_flags, -1, 0); | |||
| strcpy(word_phonemes,prefix_phonemes); | |||
| strcat(word_phonemes,phonemes); | |||
| #ifdef PLATFORM_WINDOWS | |||
| sprintf(word_phonemes, "%s%s%s", unpron_phonemes, prefix_phonemes, phonemes); | |||
| #else | |||
| snprintf(word_phonemes, sizeof(word_phonemes), "%s%s%s", unpron_phonemes, prefix_phonemes, phonemes); | |||
| #endif | |||
| word_phonemes[N_WORD_PHONEMES-1] = 0; | |||
| } | |||
| if(end_phonemes[0] != 0) | |||
| { | |||
| // a suffix had the SUFX_T option set, add the suffix after the stress pattern has been determined | |||
| strcat(word_phonemes,end_phonemes); | |||
| ix = strlen(word_phonemes); | |||
| end_phonemes[N_WORD_PHONEMES-1-ix] = 0; // ensure no buffer overflow | |||
| strcpy(&word_phonemes[ix], end_phonemes); | |||
| } | |||
| if(wflags & FLAG_LAST_WORD) | |||
| @@ -1150,7 +1177,7 @@ strcpy(phonemes2,phonemes); | |||
| dictionary_flags[0] &= ~FLAG_PAUSE1; | |||
| } | |||
| if((wflags & FLAG_HYPHEN) && (tr->langopts.stress_flags & STRS_HYPEN_UNSTRESS)) | |||
| if((wflags & FLAG_HYPHEN) && (tr->langopts.stress_flags & S_HYPEN_UNSTRESS)) | |||
| { | |||
| ChangeWordStress(tr,word_phonemes,3); | |||
| } | |||
| @@ -1237,7 +1264,7 @@ strcpy(phonemes2,phonemes); | |||
| { | |||
| // English Specific !!!! | |||
| // any single letter before a dot is an abbreviation, except 'I' | |||
| dictionary_flags[0] |= FLAG_DOT; | |||
| dictionary_flags[0] |= FLAG_ALLOW_DOT; | |||
| } | |||
| if((tr->langopts.param[LOPT_ALT] & 2) && ((dictionary_flags[0] & (FLAG_ALT_TRANS | FLAG_ALT2_TRANS)) != 0)) | |||
| @@ -2186,12 +2213,10 @@ void *TranslateClause(Translator *tr, FILE *f_text, const void *vp_input, int *t | |||
| } | |||
| } | |||
| if(option_sayas2 == SAYAS_KEY) | |||
| if((option_sayas2 == SAYAS_KEY) && (c != ' ')) | |||
| { | |||
| if(((c == '_') || (c == '-')) && IsAlpha(prev_in)) | |||
| { | |||
| c = ' '; | |||
| } | |||
| if((prev_in == ' ') && (next_in == ' ')) | |||
| option_sayas2 = SAYAS_SINGLE_CHARS; // single character, speak its name | |||
| c = towlower2(c); | |||
| } | |||
| @@ -2231,7 +2256,7 @@ void *TranslateClause(Translator *tr, FILE *f_text, const void *vp_input, int *t | |||
| } | |||
| } | |||
| else | |||
| if((option_sayas2 & 0x30) == 0) | |||
| if((option_sayas2 & 0x10) == 0) | |||
| { | |||
| // speak as words | |||
| @@ -2325,6 +2350,7 @@ if((c == '/') && (tr->langopts.testing & 2) && IsDigit09(next_in) && IsAlpha(pre | |||
| // start of word, insert space if not one there already | |||
| c = ' '; | |||
| space_inserted = 1; | |||
| next_word_flags |= FLAG_NOSPACE; | |||
| } | |||
| else | |||
| { | |||
| @@ -2402,12 +2428,21 @@ if((c == '/') && (tr->langopts.testing & 2) && IsDigit09(next_in) && IsAlpha(pre | |||
| else | |||
| if(c=='-') | |||
| { | |||
| if((IsAlpha(prev_in) || iswdigit(prev_in)) && IsAlpha(next_in)) | |||
| if(!IsSpace(prev_in) && IsAlpha(next_in)) | |||
| { | |||
| // '-' between two letters is a hyphen, treat as a space | |||
| word_flags |= FLAG_HYPHEN; | |||
| words[word_count-1].flags |= FLAG_HYPHEN_AFTER; | |||
| c = ' '; | |||
| if(prev_out != ' ') | |||
| { | |||
| // previous 'word' not yet ended (not alpha or numeric), start new word now. | |||
| c = ' '; | |||
| space_inserted = 1; | |||
| } | |||
| else | |||
| { | |||
| // '-' between two letters is a hyphen, treat as a space | |||
| word_flags |= FLAG_HYPHEN; | |||
| words[word_count-1].flags |= FLAG_HYPHEN_AFTER; | |||
| c = ' '; | |||
| } | |||
| } | |||
| else | |||
| if((prev_in==' ') && (next_in==' ')) | |||
| @@ -2433,6 +2468,18 @@ if((c == '/') && (tr->langopts.testing & 2) && IsDigit09(next_in) && IsAlpha(pre | |||
| } | |||
| } | |||
| else | |||
| if(c == '.') | |||
| { | |||
| if(!(words[word_count-1].flags & FLAG_NOSPACE) && IsAlpha(prev_in)) | |||
| { | |||
| // dot after a word, with space following, probably an abbreviation | |||
| words[word_count-1].flags |= FLAG_HAS_DOT; | |||
| if(IsSpace(next_in)) | |||
| c = ' '; // remove the dot if it's followed by a space, so that it's not pronounced | |||
| } | |||
| } | |||
| else | |||
| if(c == '\'') | |||
| { | |||
| if(iswalnum(prev_in) && IsAlpha(next_in)) | |||
| @@ -2604,9 +2651,14 @@ if((c == '/') && (tr->langopts.testing & 2) && IsDigit09(next_in) && IsAlpha(pre | |||
| words[0].pre_pause = 0; // don't add extra pause at beginning of clause | |||
| words[word_count].pre_pause = 8; | |||
| if(word_count > 0) | |||
| { | |||
| words[word_count-1].flags |= FLAG_LAST_WORD; | |||
| if((terminator & CLAUSE_DOT) && !(words[word_count-1].flags & FLAG_NOSPACE)) | |||
| words[word_count-1].flags |= FLAG_HAS_DOT; | |||
| } | |||
| words[0].flags |= FLAG_FIRST_WORD; | |||
| for(ix=0; ix<word_count; ix++) | |||
| { | |||
| int nx; | |||
| @@ -2693,11 +2745,10 @@ if((c == '/') && (tr->langopts.testing & 2) && IsDigit09(next_in) && IsAlpha(pre | |||
| } | |||
| } | |||
| } | |||
| word = pw; | |||
| pw--; | |||
| // include the next few characters, in case there are an ordinal indicator or other suffix | |||
| pn[0] = ' '; | |||
| memcpy(pn+1, pw, 16); | |||
| memcpy(pn, pw, 16); | |||
| pn[16] = 0; | |||
| for(pw = &number_buf[1]; pw < pn;) | |||
| @@ -2732,7 +2783,7 @@ if((c == '/') && (tr->langopts.testing & 2) && IsDigit09(next_in) && IsAlpha(pre | |||
| } | |||
| } | |||
| if((dict_flags & FLAG_DOT) && (ix == word_count-1) && (terminator == CLAUSE_PERIOD)) | |||
| if((dict_flags & (FLAG_ALLOW_DOT | FLAG_NEEDS_DOT)) && (ix == word_count-1) && (terminator & CLAUSE_DOT)) | |||
| { | |||
| // probably an abbreviation such as Mr. or B. rather than end of sentence | |||
| clause_pause = 10; | |||
+ 26
- 7
src/translate.h
View File
| @@ -48,7 +48,6 @@ | |||
| #define FLAG_ATEND 0x4000 /* use this pronunciation if at end of clause */ | |||
| #define FLAG_SPELLWORD 0x8000 // re-translate the word as individual letters, separated by spaces | |||
| #define FLAG_DOT 0x10000 /* ignore '.' after word (abbreviation) */ | |||
| #define FLAG_ABBREV 0x20000 // spell as letters, even with a vowel, OR use specified pronunciation rather than split into letters | |||
| #define FLAG_STEM 0x40000 // must have a suffix | |||
| @@ -57,6 +56,9 @@ | |||
| #define FLAG_ALT2_TRANS 0x200000 // language specific | |||
| #define FLAG_COMBINE 0x400000 // combine with the next word | |||
| #define FLAG_ALLOW_DOT 0x01000000 // ignore '.' after word (abbreviation) | |||
| #define FLAG_NEEDS_DOT 0x02000000 // only if the word is followed by a dot | |||
| #define FLAG_MAX3 0x08000000 // limit to 3 repeats | |||
| #define FLAG_PAUSE1 0x10000000 // shorter prepause | |||
| #define FLAG_TEXTMODE 0x20000000 // word translates to replacement text, not phonemes | |||
| @@ -100,9 +102,10 @@ | |||
| #define FLAG_SUFFIX_REMOVED 0x2000 | |||
| #define FLAG_HYPHEN_AFTER 0x4000 | |||
| #define FLAG_ORDINAL 0x8000 // passed to TranslateNumber() to indicate an ordinal number | |||
| #define FLAG_HAS_DOT 0x10000 // dot after this word | |||
| #define FLAG_NO_TRACE 0x10000 // passed to TranslateRules() to suppress dictionary lookup printout | |||
| #define FLAG_NO_PREFIX 0x20000 | |||
| #define FLAG_NO_TRACE 0x10000000 // passed to TranslateRules() to suppress dictionary lookup printout | |||
| #define FLAG_NO_PREFIX 0x20000000 | |||
| // prefix/suffix flags (bits 8 to 14, bits 16 to 22) don't use 0x8000, 0x800000 | |||
| #define SUFX_E 0x0100 // e may have been added | |||
| @@ -169,12 +172,14 @@ | |||
| // bit 16 used to distinguish otherwise identical types | |||
| // bit 20= punctuation character can be inside a word (Armenian) | |||
| // bit 21= speak the name of the punctuation character | |||
| // bit 22= dot after the last word | |||
| #define CLAUSE_BIT_SENTENCE 0x80000 | |||
| #define CLAUSE_BIT_CLAUSE 0x40000 | |||
| #define CLAUSE_BIT_VOICE 0x20000 | |||
| #define CLAUSE_BITS_INTONATION 0x7000 | |||
| #define PUNCT_IN_WORD 0x100000 | |||
| #define PUNCT_SAY_NAME 0x200000 | |||
| #define CLAUSE_DOT 0x400000 | |||
| #define CLAUSE_NONE 0 + 0x04000 | |||
| #define CLAUSE_PARAGRAPH 70 + 0x80000 | |||
| @@ -215,9 +220,9 @@ typedef struct { | |||
| // used to mark words with the source[] buffer | |||
| typedef struct{ | |||
| unsigned int flags; | |||
| unsigned short start; | |||
| unsigned short sourceix; | |||
| unsigned short flags; | |||
| unsigned char pre_pause; | |||
| unsigned char wmark; | |||
| unsigned char length; | |||
| @@ -243,7 +248,7 @@ extern const int param_defaults[N_SPEECH_PARAM]; | |||
| #define N_LOPTS 18 | |||
| #define N_LOPTS 19 | |||
| #define LOPT_DIERESES 1 | |||
| // 1=remove [:] from unstressed syllables, 2= remove from unstressed or non-penultimate syllables | |||
| // bit 4=0, if stress < 4, bit 4=1, if not the highest stress in the word | |||
| @@ -295,6 +300,7 @@ extern const int param_defaults[N_SPEECH_PARAM]; | |||
| #define LOPT_IT_DOUBLING 14 | |||
| // Call ApplySpecialAttributes() if $alt or $alt2 is set for a word | |||
| // bit 1: stressed syllable: $alt change [e],[o] to [E],[O], $alt2 change [E],[O] to [e],[o] | |||
| #define LOPT_ALT 15 | |||
| // pause for bracket (default=4), pause when annoucing bracket names (default=2) | |||
| @@ -303,6 +309,9 @@ extern const int param_defaults[N_SPEECH_PARAM]; | |||
| // bit 1, don't break clause before annoucning . ? ! | |||
| #define LOPT_ANNOUNCE_PUNCT 17 | |||
| // set minimum length for long vowels at fast speeds, to keep a distinction with short vowels | |||
| #define LOPT_MIN_LONG_VOWEL 18 | |||
| // stress_rule | |||
| #define STRESSPOSN_1L 0 // 1st syllable | |||
| @@ -321,7 +330,15 @@ typedef struct { | |||
| int vowel_pause; | |||
| int stress_rule; // 1=first syllable, 2=penultimate, 3=last | |||
| #define STRS_HYPEN_UNSTRESS 0x100000 | |||
| #define S_NO_DIM 0x02 | |||
| #define S_FINAL_DIM 0x04 | |||
| #define S_FINAL_NO_2 0x10 | |||
| #define S_NO_AUTO_2 0x20 | |||
| #define S_2_TO_HEAVY 0x40 | |||
| #define S_2_SYL_2 0x1000 | |||
| #define S_INITIAL_2 0x2000 | |||
| #define S_NO_AUTO_DIM 0x10000 | |||
| #define S_HYPEN_UNSTRESS 0x100000 | |||
| // bit0=don't stress monosyllables, except at end of clause | |||
| // bit1=don't set diminished stress, | |||
| // bit2=mark unstressed final syllables as diminished | |||
| @@ -487,6 +504,7 @@ struct Translator | |||
| // the two-letter rules for each letter must be consecutive in the language_rules source | |||
| char *groups1[256]; // translation rule lists, index by single letter | |||
| char *groups3[128]; // index by offset letter | |||
| char *groups2[N_RULE_GROUP2]; // translation rule lists, indexed by two-letter pairs | |||
| unsigned int groups2_name[N_RULE_GROUP2]; // the two letter pairs for groups2[] | |||
| int n_groups2; // number of groups2[] entries used | |||
| @@ -591,13 +609,14 @@ Translator *SelectTranslator(const char *name); | |||
| int SetTranslator2(const char *name); | |||
| void DeleteTranslator(Translator *tr); | |||
| int Lookup(Translator *tr, const char *word, char *ph_out); | |||
| int LookupFlags(Translator *tr, const char *word); | |||
| int TranslateNumber(Translator *tr, char *word1, char *ph_out, unsigned int *flags, WORD_TAB *wtab); | |||
| int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab); | |||
| void ChangeWordStress(Translator *tr, char *word, int new_stress); | |||
| void SetSpellingStress(Translator *tr, char *phonemes, int control, int n_chars); | |||
| int TranslateLetter(Translator *tr, char *letter, char *phonemes, int control, int word_length); | |||
| int TranslateLetter(Translator *tr, char *letter, char *phonemes, int control); | |||
| void LookupLetter(Translator *tr, unsigned int letter, int next_byte, char *ph_buf); | |||
| void LookupAccentedLetter(Translator *tr, unsigned int letter, char *ph_buf); | |||
+ 4
- 3
src/voices.cpp
View File
| @@ -116,6 +116,7 @@ enum { | |||
| static MNEM_TAB options_tab[] = { | |||
| {"reduce_t", LOPT_REDUCE_T}, | |||
| {"bracket", LOPT_BRACKET_PAUSE}, | |||
| {"fastLongVowel", LOPT_MIN_LONG_VOWEL}, | |||
| {NULL, -1} }; | |||
| static MNEM_TAB keyword_tab[] = { | |||
| @@ -373,9 +374,9 @@ void VoiceReset(int tone_only) | |||
| static int breath_widths[N_PEAKS] = {0,200,200,400,400,400,600,600,600}; | |||
| // default is: pitch 78,120 | |||
| voice->pitch_base = 0x45000; | |||
| voice->pitch_range = 4536; | |||
| // default is: pitch 80,118 | |||
| voice->pitch_base = 0x47000; | |||
| voice->pitch_range = 4104; | |||
| // default is: pitch 80,117 | |||
| // voice->pitch_base = 0x47000; | |||
| // voice->pitch_range = 3996; | |||
Loading…