eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

ta_rules 2.2KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205
  1. // This file is UTF8 encoded
  2. // Spelling to phoneme rules for Tamil
  3. // B means a combining vowel sign, or a virama
  4. .replace
  5. ௦ 0 // Tamil numbers
  6. ௧ 1
  7. ௨ 2
  8. ௩ 3
  9. ௪ 4
  10. ௫ 5
  11. ௬ 6
  12. ௭ 7
  13. ௮ 8
  14. ௯ 9
  15. ொ ொ
  16. ோ ோ
  17. ௌ ௌ
  18. .group 0xe0ae // characters which start with UTF-8 bytes: [e0 ae]
  19. ஂ // anusvara
  20. ஃ // visarga
  21. அ a
  22. ஆ a:
  23. இ i
  24. ஈ i:
  25. உ u
  26. ஊ u:
  27. எ e
  28. _) எ ;e // add a short [j] sound at start of word ?
  29. ஏ e:
  30. _) ஏ ;e:: // add a short [j] sound at start of word ?
  31. ஐ aI
  32. ஒ o
  33. ஓ o:
  34. ஔ aU
  35. // consonants
  36. க gV // inter-vocalic, unless there is virama before or after
  37. க (B g
  38. க (் g
  39. ்) க gV
  40. ்) க (B g
  41. _) க kV
  42. _) க (B k
  43. க்க kkV
  44. க்க (B kk
  45. ங NV
  46. ங (B N
  47. ச sV // ?? [z]
  48. ச (B s
  49. _) ச sa
  50. _) ச (B s
  51. ச்ச tS:V
  52. ச்ச (B tS:
  53. ற்ச tS:
  54. ற்ச (B tS:
  55. ட்) ச tSV
  56. ட்) ச (B tS
  57. ஞ்) ச dZV
  58. ஞ்) ச (B dZ
  59. ஜ dZV
  60. ஜ (B dZ
  61. ஞ n^V
  62. ஞ (B n^
  63. ட d.V
  64. ட (B d.
  65. _) ட t.V
  66. _) ட (B t.
  67. ட்ட t.t.V
  68. ட்ட (B t.t.
  69. ண n.V
  70. ண (B n.
  71. த dV
  72. த (B d
  73. _) த tV
  74. _) த (B t
  75. த்த ttV
  76. த்த (B tt
  77. ந nV
  78. ந (B n // dental n
  79. ன nV
  80. ன (B n // alveolar n
  81. ப bV
  82. ப (B b
  83. _) ப pV
  84. _) ப (B p
  85. ப்ப ppV
  86. ப்ப (B pp
  87. ட்) ப pV
  88. ட்) ப (B p
  89. ற்) ப pV
  90. ற்) ப (B p
  91. ஃ) ப fV
  92. ஃ) ப (B f
  93. ம mV
  94. ம (B m
  95. ய jV
  96. ய (B j
  97. ர rV
  98. ர (B r
  99. ற RV
  100. ற (B R
  101. ற் (ற t. // RR -> t.R
  102. ல lV
  103. ல (B l
  104. ள l.V
  105. ள (B l.
  106. ழ z.V
  107. ழ (B z.
  108. வ vV
  109. வ (B v
  110. ஶ SV
  111. ஶ (B S
  112. ஷ s.V
  113. ஷ (B s.
  114. ஸ sV
  115. ஸ (B s
  116. ஹ hV
  117. ஹ (B h
  118. க்ஷ ks.V
  119. க்ஷ (B ks.
  120. // combining vowels
  121. ா a:
  122. ி i
  123. .group 0xe0af // characters which start with UTF-8 bytes: [e0 af]
  124. ீ i:
  125. ு u
  126. ூ u:
  127. ெ e
  128. ே e:
  129. ை aI
  130. ொ o
  131. ோ o:
  132. ௌ aU
  133. ் // virama
  134. ௗ : // aU length mark
  135. .group 0xe0a4 // devanagari
  136. \340\244 _^_HI // switch to hindi voice
  137. .group 0xe0a5 // devanagari
  138. \340\245 _^_HI
  139. .group
  140. ் // virama
  141. $ dolV
  142. D) . (D+ _pul.l.i