From 43e37b2c7261d834ce4d68bf68480eedb1bbbcc9 Mon Sep 17 00:00:00 2001 From: Vardhan Date: Fri, 3 Feb 2017 09:17:23 +0530 Subject: [PATCH] Adding Manipuri ( sit/mni ) support --- Makefile.am | 7 + dictsource/mni_list | 218 ++++++++++--------- dictsource/mni_rules | 396 ++++++++++++++++++++++++++++++++++ docs/languages.md | 3 +- espeak-ng-data/voices/sit/mni | 2 + 5 files changed, 521 insertions(+), 105 deletions(-) create mode 100644 dictsource/mni_rules create mode 100644 espeak-ng-data/voices/sit/mni diff --git a/Makefile.am b/Makefile.am index f4884f31..bcff7a42 100644 --- a/Makefile.am +++ b/Makefile.am @@ -392,6 +392,7 @@ dictionaries: \ espeak-ng-data/lv_dict \ espeak-ng-data/mk_dict \ espeak-ng-data/ml_dict \ + espeak-ng-data/mni_dict \ espeak-ng-data/mr_dict \ espeak-ng-data/ms_dict \ espeak-ng-data/mt_dict \ @@ -724,6 +725,12 @@ dictsource/ml_extra: espeak-ng-data/ml_dict: src/espeak-ng phsource/phonemes.stamp dictsource/ml_list dictsource/ml_rules dictsource/ml_extra cd dictsource && ESPEAK_DATA_PATH=$(PWD) LD_LIBRARY_PATH=../src:${LD_LIBRARY_PATH} ../src/espeak-ng --compile=ml && cd .. +mni: espeak-ng-data/mni_dict +dictsource/mni_extra: + touch dictsource/mni_extra +espeak-ng-data/mni_dict: src/espeak-ng phsource/phonemes.stamp dictsource/mni_list dictsource/mni_rules dictsource/mni_extra + cd dictsource && ESPEAK_DATA_PATH=$(PWD) LD_LIBRARY_PATH=../src:${LD_LIBRARY_PATH} ../src/espeak-ng --compile=mni && cd .. + mr: espeak-ng-data/mr_dict dictsource/mr_extra: touch dictsource/mr_extra diff --git a/dictsource/mni_list b/dictsource/mni_list index aed74705..c39db730 100644 --- a/dictsource/mni_list +++ b/dictsource/mni_list @@ -1,135 +1,142 @@ - // Translation rules for Manipuri // This file is UTF8 encoded // Numbers // numbers are changed to latin characters before translation -_0 sino // or p#'un'b'O ?? -_1 ama: -_2 ani -_3 ahu'm -_4 mari -_5 ma'Nga: -_6 tar'uk -_7 tar'et -_8 nipa:n +_0 suinO // or p#'un'b'O ?? +_1 am:a: +_2 a:n,'i +_3 a,hu'm +_4 ma:,ri +_5 ma'N~a: +_6 tar:u:kk +_7 tar:et +_8 ni,pa:n _9 ma:pa:n - -_10 ta'ra: -_11 tara:m'thOi -_12 tara:ni'thOi -_13 tara:h'um'dOi -_14 tara:ma'ri -_15 tara:ma'Nga: +_1a camma +_2a tSa:ni // two hundreds etc +_3a tSahum +_4a tSamri +_5a tsam'N~a +_6a tSa'trUk +_7a tSat'ret. +_8a tSani,pan +_9a tSama,pal +_10 't.a:ra +_11 tara:'mathOi +_12 tara:ni't#Oi +_13 'tarahumd,Oi +_14 tar.a:ma'r:i +_15 tara:ma'N~a: _16 tara:ta:ruk _17 tara:tar'et _18 tara:nipa:n _19 tara:mapa:n -_20 kun. -_21 kunma:thOi -_22 kuni'thOi -_23 kun.hum'dOi -_24 kun'ma:ri -_25 kun'maNg'a: +_20 ku:n. +_21 ku:n.ma:thOi +_22 ku:ni'thOi +_23 ku:n.hum'dOi +_24 ku:n'ma:ri +_25 ku:n'maN~'a: _26 kun'ta:ruk _27 kun'tar'et _28 kun'nipa:n _29 kun'mapa:n -_30 kun't#'ra: -_31 kun't#'ra:m'thOi -_32 kun't#'ra:ni'thOi -_33 kun't#'ra:um'dOi -_34 kun't#'ra:ma:ri -_35 kun't#'ra:maNg'a: -_36 kun't#'ra:ta:ruk -_37 kun't#'ra:tar'et -_38 kun't#'ra:nipa:n -_39 kun't#'ra:mapa:n +_30 k,u:n't#'ra: +_31 k,u:n't#'ra:ma'thOi +_32 k,u:n't#'ra:ni'thOi +_33 k,u:n't#'ra:hum'dOi +_34 k,u:n't#'ra:ma:ri +_35 k,u:n't#'ra:maN~'a: +_36 k,u:n't#'ra:ta:ruk +_37 k,u:n't#'ra:tar'et +_38 k,u:n't#'ra:nipa:n +_39 k,u:n't#'ra:mapa:n _40 nifu _41 nifuma:t#Oi _42 nifu'nit#Oi -_43 nifum'dOi +_43 nifu,hum'dOi _44 nifu'ma:ri -_45 nifu'maNg'a: -_46 nifu'ta:ruk -_47 nifu'tar'et -_48 nifu'nipa:n -_49 nifu'mapa:n +_45 nifu'maN~'a: +_46 ni,futa:ruk +_47 ni,futar'et +_48 ni,funipa:n +_49 ni,fumapa:n -_50 j@Ngk#@i -_51 j@Ngk#@i'ma:t#Oi -_52 j@NgkhO'i'ni't#Oi -_53 j@NgkhO'i'hum'dOi -_54 j@NgkhO'ima:ri -_55 j@NgkhO'imaNg'a: -_56 j@NgkhO'ita:ruk -_57 j@NgkhO'itar'et -_58 j@NgkhO'ini'pa:n -_59 j@NgkhO'ima'pa:n +_50 j:aN~k#ai +_51 j:aN~k#aima:t#Oi +_52 j:aN~k#aini't#Oi +_53 j:aN~k#aihum'dOi +_54 j:aN~k#aiima:ri +_55 j:aN~k#aimaN~'a: +_56 j:aN~k#aita:ruk +_57 j:aN~k#aitar'et +_58 j:aN~k#aini'pa:n +_59 j:aN~k#ai,map:al +_60 h,umfu +_61 h,umfu,ma:t#Oi +_62 h,umfu,ni't#Oi +_63 h,umfu,hum'dOi +_64 h,umfu,ma:ri +_65 h,umfu,maN~'a: +_66 h,umfu,ta:ruk +_67 h,umfu,tar'et +_68 h,umfu,ni'pa:n +_69 h,umfu,ma'pa:n -_60 hum'fu -_61 hum'fu'ma:t#Oi -_62 hum'fu'ni't#Oi -_63 hum'fu'hum'dOi -_64 hum'fu'ma:ri -_65 hum'fu'maNg'a: -_66 hum'fu'ta:ruk -_67 hum'fu'tar'et -_68 hum'fu'ni'pa:n -_69 hum'fu'ma'pa:n - -_70 hum'dra: -_71 hum'dra:ma:t#Oi -_72 hum'dra:ni't#Oi -_73 hum'dra:hum'dOi -_74 hum'dra:ma:ri -_75 hum'dra:maNg'a: -_76 hum'dra:ta:ruk -_77 hum'dra:tar'et -_78 hum'dra:ni'pa:n -_79 hum'dra:ma'pa:n +_70 hu,mdra: +_71 hum,dra:ma:t#Oi +_72 hum,dra:ni't#Oi +_73 hum,dra:hum'dOi +_74 hum,dra:ma:ri +_75 hum,dra:maN~'a: +_76 hum,dra:ta:ruk +_77 hum,dra:tar'et +_78 hum,dra:ni'pa:n +_79 hum,dra:ma'pa:n -_80 ma:ri'fu -_81 ma:ri'fu'ma:t#Oi -_82 ma:ri'fu'ni't#Oi -_83 ma:ri'fu'hum'dOi -_84 ma:ri'fu'ma:ri -_85 ma:ri'fu'maNg'a: -_86 ma:ri'fu'ta:ruk -_87 ma:ri'fu'tar'et -_88 ma:ri'fu'nipa:n -_89 ma:ri'fu'mapa:n +_80 ma:rfu +_81 ma:r'fu,ma:,t#Oi +_82 ma:r'fu,ni',t#Oi +_83 ma:r'fu,hum',dOi +_84 ma:r'fu,ma:r,i +_85 ma:r'fu,maN~'a: +_86 ma:r'fu,ta:ruk +_87 ma:r'fu,tar'et +_88 ma:r'fu,nipa:n +_89 ma:r'fu,mapa:n _90 mO'ud'ra: -_91 mO'ud'ra:ma:t#Oi -_92 mO'ud'ra:ni't#Oi -_93 mO'ud'ra:hum'dOi -_94 mO'ud'ra:ma:ri -_95 mO'ud'ra:maNg'a: -_96 mO'ud'ra:ta:ruk -_97 mO'ud'ra:tar'et -_98 mO'ud'ra:ni'pa:n -_99 mO'ud'ra:mapa:n +_91 mO'ud'ra:,ma:t#Oi +_92 mO'ud'ra:,ni't#Oi +_93 mO'ud'ra:,hum'dOi +_94 mO'ud'ra:,ma:ri +_95 mO'ud'ra:,maN~'a: +_96 mO'ud'ra:,ta:ruk +_97 mO'ud'ra:,tar'et +_98 mO'ud'ra:,ni'pa:n +_99 mO'ud'ra:,mapa:n -_100 c#@m'ma: -_0M1 l'isiN +_C c#@m'ma: +_0M1 lisiN~ +_0M2 l'ak# _dpt _ d'Osomik_ // Single consonants -ক kO -খ k#@ +ক k:O +খ k#O গ gO -ঘ g#@ -ঙ 'uNgO~ +ঘ g#O +ঙ 'N~O~ চ tSO -ছ tShO // [h] to distinguish from [tS] +ছ chO // [h] to distinguish from [tS] জ JO ঝ J#@ ঞ 'iNO~ @@ -160,22 +167,22 @@ _dpt _ d'Osomik_ ষ m,ud#en:oS:'O স d,onteS:'O হ hO -ৎ khOndot'O +ৎ khOndott'O // full vowels অ O আ a -ই hrOS:o'i -ঈ d'i:rg#o'i -উ hrOS:o'u +ই rOS:e'i +ঈ I +উ u ঊ d'i:rg#o'u _এ e _ঐ oj _ও o _ঔ ow - - + + @@ -192,8 +199,8 @@ _ঔ ow ৌ 'owkar // signs -ং 'OnuSSOr -ঃ b'iSOrgo // sparingly used +ং 'OnuN~sOr +ঃ b'isOrgo // sparingly used ঁ tS'Ondrobindu // sparingly used @@ -203,4 +210,7 @@ _, koma _? ahONg'ba:khudam _! Ng'kapa:khudam +// exception words + _)ঈ(_ I // blood + ফল f@l diff --git a/dictsource/mni_rules b/dictsource/mni_rules new file mode 100644 index 00000000..cb31ef9a --- /dev/null +++ b/dictsource/mni_rules @@ -0,0 +1,396 @@ +// Pronounciation rule for Manipuri. +// This file is UTF8 encoded + +// letter groups: +// A vowel letters and vowel signs +// B vowel signs and virama ् +// C consonants +// Y vowel letters and vowel signs + + + +.replace + ০ 0 + ১ 1 + ২ 2 + ৩ 3 + ৪ 4 + ৫ 5 + ৬ 6 + ৭ 7 + ৮ 8 + ৯ 9 + + +// Vowels + + +.group অ + অ @ + অঁ O~ + অ্যা & // V,ja in [æmiba] + + +.group আ + আ a: + আঁ a~ + +.group ই + ই i + ইঁ i~ + + +.group ঈ + ঈ i + ঈঁ i~ + _)ঈ(_C i + + +.group উ + উ u + উঁ u~ + + +.group ঊ + ঊ u + ঊঁ u~ + + +.group ঐ + ঐ oj + ঐঁ o~j + + +.group এ + এ e + এঁ e~ + + এ্যা & // e,ja [ækademi] + + +.group ও + ও o + ওঁ o~ + + +.group ঔ + ঔ ow + ঔঁ o~w + +.group ও //?? + ও o: + + + + +// Vowel Signs + +.group া + C) া a + C) াঁ a~ + +.group ি + C) ি i + C) িঁ i~ + +.group ী + C) ী i + C) ীঁ i~ + +.group ূ + C) ূ u + C) ূঁ u~ + +.group ু + C) ু u + C) ুঁ u~ + +.group ৃ + C) ৃ r'i + C) ৃঁ r'i~ + +.group ে + C) ে e + C) েঁ e~ + C) েউ ew + +.group ৈ + C) ৈ oj + C) ৈঁ o~j + +.group ো + C) ো o + C) োঁ o~ + +.group ৌ + C) ৌ ow + C) ৌঁ o~w + + + +// Consonants + +.group ক + ক k@ + ক (B k + ক (C kO + _)ক (C kO + _)ক (B k + +.group খ + খ kh@ + খ (B kh + _)খ (C khO + _)খ (B kh + +.group গ + গ g@ + গ (B g + গ (C g + _)গ (C g@ + _)গ (B g + +.group ঘ + ঘ g#@ + ঘ (B gh + ঘ (C gh@ + _)ঘ (C gh@ + _)ঘ (B gh + +.group ঙ + ঙ Ng + ঙ (B N~ + _)ঙ (B N~ + +.group চ + চ c@ + চ (B c + চ(C c@ + _)চ(C c@ + _)চ(B c + +.group ছ + ছ chO + ছ (B ch + _)ছ (B ch + _)ছ (C chO + + +.group জ + জ J@ + জ (B J + জ (_ J + জ (C J + C)জ (C J@ + _)জ (C J@ + _)জ (B J + জ্ব JV + জ্ব (B J + জ্ঞ ggo~ + জ্ঞ (B gg~ + + + +.group ঝ + ঝ Jh@ + ঝ (B Jh + _)ঝ (B Jh + _)ঝ (C JhO + +.group ঞ + ঞ nV + ঞ (B n + জ)ঞ (B gg + + +.group ট + ট t.O + ট (B t. + _)ট (B t. + _)ট (C t.O + + +.group ঠ + ঠ thO + ঠ (B t.h + _)ঠ (B t.h + _)ঠ (C t.hO + + +.group ড + ড d.O + ড (B d. + _)ড (B d. + _)ড (C d.O + + ড় r. // nukta + ড় (B r. + + +.group ঢ + ঢ d.h + ঢ (B d.h + _)ঢ (C d.hO + + ঢ় hr. + ঢ় (B hr. + + +.group ণ + ণ nO + ণ (B n + + + +.group ত + ত t + ত (B t + ত (C t + ত (_ to + _)ত (C to + +.group থ + থ thO + থ (B th + থ (_ thO + _)থ (B th + _)থ (C thO + +.group দ + দ dO + দ (B d + দ (_ dO + _)দ (C dO + +.group ধ + ধ dhO + ধ (B dh + _)ধ (C dhO + +.group ন + ন nO + ন (B n + _)ন (B n + ন (C nO + _)ন (C nO +.group প + প pO + প (B p + _)প(C pO + _)প(B p + প (_ p + +.group ফ + ফ fO + ফ (B f + _)ফ (B f + _)ফ (C fa + ফ (C fO + +.group ব + ব bO + ব (B b + _)ব(C bO + ব(_ b + + +.group ভ + ভ bh@ + ভ (B bh + ভ (C bhO + ভ (_ bh + +.group ম + ম m@ + ম (B m + _)ম (C m@ + _)ম (B m + ম (C m@ + +.group য + য dZ@ + য (B dZ + য (C dZ + _)য(C dZO + + য় j@ // nukta + _) য় (B j@ + +.group র + র r@ + র (B r + র (_ r + _)র (C r@ + +.group ল + ল l@ + ল (B l + ল (_ l + ল (C l@ +.group ৱ + ৱ wa + ৱ (B w@ + ৱ (C w@ + _) ৱ (B w@ + _) ৱ (C w@ + +.group শ + শ S@ // or [s] ? + শ (B S + শ (C S + _)শ (C S@ +.group ষ + ষ S@ + ষ (B S + _)ষ (C S@ + +.group স + স s@ / + স (B S + _)স (C sa + স (C s@ + +.group হ + হ h@ + হ (B h + হ (_ h + _) হ (C h@ + +.group ক্ষ + ক্ষ k#k#@ + ক্ষ (B k#k# + ক্ষ (C k#k# + + +.group ড় // rarely used + ড় r. + ড় (B r. + + +.group ঢ় // rarely used, or not used? + ঢ় hr. + ঢ় (B hr. + ঢ় (_ hr.o + +.group য় + য় j@ + _)য়(B j@ + য়(B j@ + + +.group ং + A)ং N + C)ং N + +.group ঃ // visarga/bishorgo + ঃ // doubles the following consonant + ঃ (_ H + +.group ্ // virama/hoshonto + C) ্ + +.group ৎ //khOndott'O + C)ৎ t + +.group ় + ় // nukta, modifies a consonant diff --git a/docs/languages.md b/docs/languages.md index 73e5985a..7082a423 100644 --- a/docs/languages.md +++ b/docs/languages.md @@ -76,6 +76,7 @@ The supported languages are: | `poz` | `ms` | Malayo-Polynesian | Malay | | | `dra` | `ml` | Dravidian | Malayalam | | | `sem` | `mt` | Semitic | Maltese | | +| `sit` | `mni` | Sino-Tibetan | Manipuri | | | `inc` | `mr` | Indic | Marathi | | | `azc` | `nci` | Uto-Aztecan | Nahuatl | Classical | | `inc` | `ne` | Indic | Nepali | | @@ -117,4 +118,4 @@ The supported languages are: [4] Currently, only Hiragana and Katakana are supported. -[5] Currently only supported using the `[[...]]` phoneme blocks. \ No newline at end of file +[5] Currently only supported using the `[[...]]` phoneme blocks. diff --git a/espeak-ng-data/voices/sit/mni b/espeak-ng-data/voices/sit/mni new file mode 100644 index 00000000..bb83193b --- /dev/null +++ b/espeak-ng-data/voices/sit/mni @@ -0,0 +1,2 @@ +name manipuri +language mni