Issue #763: add initial support for Uyghur language

espeak-ng · May 29, 2020 · 3a0392f · 3a0392f
1 parent 6e41dde
commit 3a0392f
Show file tree

Hide file tree

Showing 8 changed files with 273 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -30,6 +30,7 @@ new languages:
 *  uk (Ukrainian) -- Valdis Vitolins
 *  qu (Quechua) -- Valdis Vitolins
 *  tk (Turkmen) -- boracasli98, Valdis Vitolins
+*  ug (Uyghur) -- boracasli98, Valdis Vitolins
 
 ### 1.50 - 2019-11-29
 

diff --git a/Makefile.am b/Makefile.am
@@ -394,6 +394,7 @@ phsource/phonemes.stamp: \
 	phsource/ph_tibetan \
 	phsource/ph_turkish \
 	phsource/ph_turkmen \
+	phsource/ph_uyghur \
 	phsource/ph_urdu \
 	phsource/ph_uzbek \
 	phsource/ph_vietnam \
@@ -555,6 +556,7 @@ dictionaries: \
 	espeak-ng-data/tr_dict \
 	espeak-ng-data/tt_dict \
 	espeak-ng-data/uk_dict \
+	espeak-ng-data/ug_dict \
 	espeak-ng-data/ur_dict \
 	espeak-ng-data/uz_dict \
 	espeak-ng-data/vi_dict \
@@ -857,6 +859,9 @@ espeak-ng-data/tr_dict: dictsource/tr_list dictsource/tr_rules dictsource/tr_ext
 tt: espeak-ng-data/tt_dict
 espeak-ng-data/tt_dict: dictsource/tt_list dictsource/tt_rules dictsource/tt_extra
 
+ug: espeak-ng-data/ug_dict
+espeak-ng-data/ug_dict: dictsource/ug_list dictsource/ug_rules dictsource/ug_extra
+
 uk: espeak-ng-data/uk_dict
 espeak-ng-data/uk_dict: dictsource/uk_list dictsource/uk_rules dictsource/uk_extra
 

diff --git a/dictsource/ug_list b/dictsource/ug_list
@@ -0,0 +1 @@
+// This is currently empty
diff --git a/dictsource/ug_rules b/dictsource/ug_rules
@@ -0,0 +1,204 @@
+// Uyghur
+
+.group a
+        a        A
+
+.group b
+        b        b
+
+.group c
+        ch       tS
+
+.group d
+        d        d
+
+.group e
+        e        &
+
+.group é
+        é        e
+
+.group f
+        f        f
+
+.group g
+        g        g
+        g'h      gh
+        gh       Q"
+
+.group h
+        h        h
+
+.group i
+        i        I
+
+.group j
+        j        dZ
+
+.group k
+        k        k
+
+.group l
+        l        l
+
+.group m
+        m        m
+
+.group n
+        n        n
+        n'g      ng
+        ng       N
+
+.group o
+        o        o
+
+.group ö
+        ö        W
+
+.group p
+        p        p
+
+.group q
+        q        q
+
+.group r
+        r        R
+
+.group s
+        s        s
+        s'h      sh
+        sh       S
+
+.group t
+        t        t
+
+.group u
+        u        u
+
+.group ü
+        ü        y
+
+.group w
+        w        w
+
+.group x
+        x        X
+
+.group y
+        y        j
+
+.group z
+        z        z
+        z'h      zh
+        zh       Z
+
+.group ئ
+        ئ
+        ئا       A
+        ئە       &
+        ئې       e
+        ئى       I
+        ئو       o
+        ئۆ       W
+        ئۇ       u
+        ئۈ       y
+
+.group ا
+        ا        A
+
+.group ب
+        ب        b
+
+.group چ
+        چ        tS
+
+.group د
+        د        d
+
+.group ە
+        ە        &
+
+.group ې
+        ې        e
+
+.group ف
+        ف        f
+
+.group گ
+        گ        g
+        گھ       gh
+
+.group غ
+        غ        Q"
+
+.group ھ
+        ھ        h
+
+.group ى
+        ى        I
+
+.group ج
+        ج        dZ
+
+.group ك
+        ك        k
+
+.group ل
+        ل        l
+
+.group م
+        م        m
+
+.group ن
+        ن        n
+        نگ       ng
+
+.group ڭ
+        ڭ        N
+
+.group و
+        و        o
+
+.group ۆ
+        ۆ        W
+
+.group پ
+        پ        p
+
+.group ق
+        ق        q
+
+.group ر
+        ر        R
+
+.group س
+        س        s
+        سھ       sh
+
+.group ش
+        ش        S
+
+.group ت
+        ت        t
+
+.group ۇ
+        ۇ        u
+
+.group ۈ
+        ۈ        y
+
+.group ۋ
+        ۋ        w
+
+.group خ
+        خ        X
+
+.group ي
+        ي        j
+
+.group ز
+        ز        z
+        زھ       zh
+
+.group ژ
+        ژ        Z
diff --git a/docs/languages.md b/docs/languages.md
@@ -8,7 +8,7 @@ and dialects,
 [private-use extensions](https://raw.githubusercontent.com/espeak-ng/bcp47-data/master/bcp47-extensions)
 have been used.
 
-The 116 supported languages and accents are:
+The 117 supported languages and accents are:
 
 | Family Code | Identifier        | Language Family       | Language                    | Accent/Dialect         |
 |-------------|-------------------|-----------------------|-----------------------------|------------------------|
@@ -122,6 +122,7 @@ The 116 supported languages and accents are:
 | `trk`       | `tt`              | Turkic                | Tatar                       |                        |
 | `dra`       | `te`              | Dravidian             | Telugu                      |                        |
 | `trk`       | `tr`              | Turkic                | Turkish                     |                        |
+| `trk`       | `ug`              | Turkic                | Uyghur<sup>\[5,6\]</sup>    |                        |
 | `inc`       | `ur`              | Indic                 | Urdu                        |                        |
 | `trk`       | `uz`              | Turkic                | Uzbek                       |                        |
 | `aav`       | `vi-vn-x-central` | Austroasiatic         | Vietnamese                  | Central Vietnam        |
@@ -139,4 +140,6 @@ The 116 supported languages and accents are:
 
 \[5\] With Latin alphabet.
 
+\[6\] With Arabic alphabet.
+
 
diff --git a/espeak-ng-data/lang/trk/ug b/espeak-ng-data/lang/trk/ug
@@ -0,0 +1,2 @@
+name Uyghur
+language ug
diff --git a/phsource/ph_uyghur b/phsource/ph_uyghur
@@ -0,0 +1,53 @@
+phoneme A
+  vwl starttype #a endtype #a
+  length 200
+  FMT(vowel/aa_9)
+endphoneme
+
+phoneme &
+  vwl starttype #a endtype #a
+  flag1
+  length 200
+  FMT(vowel/ee_2)
+endphoneme
+
+phoneme e
+  vwl starttype #e endtype #e
+  length 200
+  flag1
+  FMT(vdiph2/ii@_2)
+endphoneme
+
+phoneme I
+  vwl starttype #@ endtype #@
+  flag1
+  length 100
+  IF thisPh(isWordEnd) THEN
+    length 140
+  ENDIF
+  FMT(vowel/ii#)
+endphoneme
+
+phoneme o
+  vwl starttype #o endtype #o
+  length 200
+  FMT(vowel/o_3)
+endphoneme
+
+phoneme W
+  vwl starttype #@ endtype #@
+  length 200
+  FMT(vowel/y#)
+endphoneme
+
+phoneme u
+  vwl starttype #u endtype #u
+  length 200
+  FMT(vowel/u_bck3)
+endphoneme
+
+phoneme y
+  vwl starttype #u endtype #u
+  length 200
+  FMT(vowel/y_5)
+endphoneme
diff --git a/phsource/phonemes b/phsource/phonemes
@@ -2016,6 +2016,9 @@ include ph_azerbaijani
 phonemetable tk tr
 include ph_turkmen
 
+phonemetable ug tr
+include ph_uyghur
+
 phonemetable pt-pt pt
 include ph_portugal