docs: Document the lexical set transcriptions used by the en language files.

docs/languages/gmw/en.md

@@ -15,60 +15,66 @@ Sets<sup>\[<a href="#ref1">1</a>\]</sup>. These were created by Wells in 1982
 by comparing the Received Pronunciation British (RP) and General American
 (GenAm) accents in use at that time.
 
+The `en` transcriptions listed below are the phonemes used by eSpeak NG to
+transcribe the different lexical sets.
+
 ## Short Vowels
 
-| Lexical Set | RP    | GenAm |
-|-------------|-------|-------|
-| KIT         | ɪ     | ɪ     |
-| DRESS       | e     | ɛ     |
-| TRAP        | æ     | æ     |
-| LOT         | ɒ     | ɑ     |
-| STRUT       | ʌ     | ʌ     |
-| FOOT        | ʊ     | ʊ     |
+| Lexical Set | en    | RP    | GenAm |
+|-------------|-------|-------|-------|
+| KIT         | `I`   | ɪ     | ɪ     |
+| DRESS       | `E`   | e     | ɛ     |
+| TRAP        | `a`   | æ     | æ     |
+| LOT         | `0`   | ɒ     | ɑ     |
+| STRUT       | `V`   | ʌ     | ʌ     |
+| FOOT        | `U`   | ʊ     | ʊ     |
 
 ## Long Vowels
 
-| Lexical Set | RP    | GenAm |
-|-------------|-------|-------|
-| FLEECE      | iː    | i     |
-| PALM        | ɑː    | ɑ     |
-| THOUGHT     | ɔː    | ɔ     |
-| GOOSE       | uː    | u     |
+| Lexical Set | en    | RP    | GenAm |
+|-------------|-------|-------|-------|
+| FLEECE      | `i:`  | iː    | i     |
+| PALM        | `A:`  | ɑː    | ɑ     |
+| THOUGHT     | `O:`  | ɔː    | ɔ     |
+| GOOSE       | `u:`  | uː    | u     |
 
 ## Rhotic Vowels
 
 These are vowels that are followed by an `r` that is not part of the next syllable
 when considering the root form of the word containing that vowel.
 
-| Lexical Set | RP    | GenAm |
-|-------------|-------|-------|
-| NURSE       | ɜː    | ɝ     |
-| START       | ɑː    | ɑɹ    |
-| NORTH       | ɔː    | ɔɹ    |
-| FORCE       | ɔː    | oɹ    |
-| CURE        | ʊə̯     | ʊɹ    |
-| NEAR        | ɪə̯     | ɪɹ    |
-| SQUARE      | eə̯     | ɛɹ    |
+| Lexical Set | en    | RP    | GenAm |
+|-------------|-------|-------|-------|
+| NURSE       | `3:`  | ɜː    | ɝ     |
+| START       | `A@`  | ɑː    | ɑɹ    |
+| NORTH       | `O@`  | ɔː    | ɔɹ    |
+| FORCE       | `o@`  | ɔː    | oɹ    |
+| CURE        | `U@`  | ʊə̯     | ʊɹ    |
+| NEAR        | `i@3` | ɪə̯     | ɪɹ    |
+| SQUARE      | `e@`  | eə̯     | ɛɹ    |
+
+__NOTE:__ `/i@3/` is used for the NEAR lexical set to differentiate it from
+`/i@/` used in words like `million`.
 
 ## Reduced Vowels
 
 These are unstressed vowels that differ from the vowels in the main lexical sets.
 
-| Lexical Set | RP    | GenAm |
-|-------------|-------|-------|
-| HAPPY       | ɪ     | i     |
-| COMMA       | ə     | ə     |
-| LETTER      | ə     | ɚ     |
+| Lexical Set | en    | RP    | GenAm |
+|-------------|-------|-------|-------|
+| HAPPY       | `i`   | ɪ     | i     |
+| COMMA       | `@`   | ə     | ə     |
+| LETTER      | `3`   | ə     | ɚ     |
 
 ## Diphthongs
 
-| Lexical Set | RP    | GenAm |
-|-------------|-------|-------|
-| FACE        | eɪ̯     | eɪ̯     |
-| PRICE       | aɪ̯     | aɪ̯     |
-| CHOICE      | ɔɪ̯     | ɔɪ̯     |
-| GOAT        | əʊ̯     | oʊ̯     |
-| MOUTH       | aʊ̯     | aʊ̯     |
+| Lexical Set | en    | RP    | GenAm |
+|-------------|-------|-------|-------|
+| FACE        | `eI`  | eɪ̯     | eɪ̯     |
+| PRICE       | `aI`  | aɪ̯     | aɪ̯     |
+| CHOICE      | `OI`  | ɔɪ̯     | ɔɪ̯     |
+| GOAT        | `oU`  | əʊ̯     | oʊ̯     |
+| MOUTH       | `aU`  | aʊ̯     | aʊ̯     |
 
 ## Split Vowels
 
@@ -76,10 +82,15 @@ These are lexical sets defined by John Wells that are merged with other lexical
 sets in both RP and GenAm, so have split from one of those lexical sets and
 merged with the other.
 
-| Lexical Set | RP    | GenAm |
-|-------------|-------|-------|
-| BATH        | ɑː    | æ     |
-| CLOTH       | ɒ     | ɔ     |
+| Lexical Set | en    | RP    | GenAm |
+|-------------|-------|-------|-------|
+| BATH        | `aa`  | ɑː    | æ     |
+| CLOTH       | `0`   | ɒ     | ɔ     |
+
+__NOTE:__ eSpeak NG does not have a distinct transcription for the CLOTH lexical
+set. As such, it can only represent American English accents with the COT-CAUGHT
+merger where COT is the American PALM-LOT merger and CAUGHT is the American
+THOUGHT-CLOTH merger.
 
 ## References
 

phsource/ph_english

@@ -97,7 +97,7 @@ endphoneme
 // VOWELS
 //*******************************************************************
 
-phoneme @    //  Schwa
+phoneme @
   vwl   starttype #@  endtype #@
   unstressed
   length 140
@@ -109,7 +109,7 @@ phoneme @    //  Schwa
 endphoneme
 
 
-phoneme 3    //  Schwa, used for rhotic schwa in American, e.g. bett**er**
+phoneme 3
   CALL @
   ipa ə
 endphoneme
@@ -178,7 +178,7 @@ phoneme a# // **a**bout. This may be \[@\] or may be a more open schwa.
 endphoneme
 
 
-phoneme aa   //   'b**a**th' etc. This is \[a\] in some accents, \[A:\] in others.
+phoneme aa
   vwl  starttype #a  endtype #a
   ipa a
   length 200
@@ -192,7 +192,7 @@ phoneme aa   //   'b**a**th' etc. This is \[a\] in some accents, \[A:\] in other
 endphoneme
 
 
-phoneme E // dr**e**ss
+phoneme E
   vwl  starttype #e  endtype #e
   length 140
   IF nextPhW(n) THEN
@@ -223,7 +223,7 @@ endphoneme
 
 
 
-phoneme I // k**i**t
+phoneme I
   vwl  starttype #i  endtype #i
   length 130
   IfNextVowelAppend(;)
@@ -263,7 +263,7 @@ phoneme I#   // used for [I] which may be [@] in some accents
 endphoneme
 
 
-phoneme i   // happ**y**. optional variant of [I] for end of words
+phoneme i
   vwl  starttype #i  endtype #i
   unstressed
   ipa i
@@ -278,7 +278,7 @@ phoneme i   // happ**y**. optional variant of [I] for end of words
 endphoneme
 
 
-phoneme 0 // l**o**t
+phoneme 0
   vwl  starttype #o  endtype #o
   length 140
   ChangeIfDiminished(@)
@@ -304,7 +304,7 @@ phoneme 02   // becomes V in en-us
 endphoneme
 
 
-phoneme V // str**u**t
+phoneme V
   vwl  starttype #a  endtype #@
   length 140
 
@@ -313,7 +313,7 @@ phoneme V // str**u**t
 endphoneme
 
 
-phoneme U // f**oo**t
+phoneme U
   vwl  starttype #o  endtype #o
   length 150
   
@@ -327,7 +327,7 @@ endphoneme
 
 
 
-phoneme A: // p**al**m
+phoneme A:
   vwl  starttype #a  endtype #a
   length 230
   IfNextVowelAppend(r-)
@@ -335,7 +335,7 @@ phoneme A: // p**al**m
 endphoneme
 
 
-phoneme A@     // st**ar**t. Used for [A:] when followed by 'r'.
+phoneme A@
   vwl  starttype #a  endtype #a
   ipa ɑː
   length 230
@@ -352,7 +352,7 @@ endphoneme
 
 
 
-phoneme 3: // n**ur**se
+phoneme 3:
   vwl  starttype #@  endtype #@
   length 210
   IfNextVowelAppend(r-)
@@ -361,7 +361,7 @@ phoneme 3: // n**ur**se
 endphoneme
 
 
-phoneme i: // fl**ee**ce
+phoneme i:
   vwl  starttype #i  endtype #i
   length 175
   IfNextVowelAppend(;)
@@ -372,7 +372,7 @@ phoneme i: // fl**ee**ce
 endphoneme
 
 
-phoneme O: // th**ou**ght
+phoneme O:
   vwl  starttype #o  endtype #o
   length 230
   ChangeIfDiminished(@)
@@ -388,7 +388,7 @@ phoneme O
 endphoneme
 
 
-phoneme O@ // n**or**th
+phoneme O@
   vwl  starttype #o  endtype #o
   ipa ɔː
   length 240
@@ -397,7 +397,7 @@ phoneme O@ // n**or**th
 endphoneme
 
 
-phoneme o@ // f**or**ce
+phoneme o@
   vwl  starttype #o  endtype #o
   ipa ɔː
   length 250
@@ -411,7 +411,7 @@ phoneme o@ // f**or**ce
 endphoneme
 
 
-phoneme u: // g**oo**se
+phoneme u:
   vwl  starttype #u  endtype #u
   length 210
   IF nextPh(l/2) THEN
@@ -424,14 +424,14 @@ phoneme u: // g**oo**se
 endphoneme
 
 
-phoneme aU // m**ou**th
+phoneme aU
   vwl  starttype #a  endtype #u
   length 230
   FMT(vdiph/au)
 endphoneme
 
 
-phoneme oU // g**oa**t
+phoneme oU
   vwl  starttype #@  endtype #u
   ipa əʊ
   length 220
@@ -453,7 +453,7 @@ phoneme oU#
 endphoneme
 
 
-phoneme aI // pr**i**ce
+phoneme aI
   vwl  starttype #a  endtype #i
   length 240
   IF nextPh(#a) THEN
@@ -463,21 +463,21 @@ phoneme aI // pr**i**ce
 endphoneme
 
 
-phoneme eI // f**a**ce
+phoneme eI
   vwl  starttype #e  endtype #i
   length 210
   FMT(vdiph/eei)
 endphoneme
 
 
-phoneme OI // ch**oi**ce
+phoneme OI
   vwl  starttype #o  endtype #i
   length 230
   FMT(vdiph/ooi)
 endphoneme
 
 
-phoneme e@ // squ**are**
+phoneme e@
   vwl  starttype #e  endtype #@
   length 230
   IfNextVowelAppend(r-)
@@ -485,7 +485,7 @@ phoneme e@ // squ**are**
 endphoneme
 
 
-phoneme i@ // mill**io**n
+phoneme i@
   vwl  starttype #i  endtype #@
   length 250
   IfNextVowelAppend(r-)
@@ -493,7 +493,7 @@ phoneme i@ // mill**io**n
 endphoneme
 
 
-phoneme i@3 // n**ear**
+phoneme i@3
   vwl  starttype #i  endtype #@
   length 250
   
@@ -506,7 +506,7 @@ phoneme i@3 // n**ear**
 endphoneme
 
 
-phoneme U@ // c**ure**
+phoneme U@
   vwl  starttype #u  endtype #@
   length 200
   IfNextVowelAppend(r-)