diff --git a/dictionaries/.gitignore b/dictionaries/.gitignore index 1d76c630..307afed5 100644 --- a/dictionaries/.gitignore +++ b/dictionaries/.gitignore @@ -1,2 +1,3 @@ +*.py *.txt !opencpop* diff --git a/dictionaries/opencpop-strict.txt b/dictionaries/opencpop-strict.txt index c00d54b5..401a0110 100644 --- a/dictionaries/opencpop-strict.txt +++ b/dictionaries/opencpop-strict.txt @@ -141,9 +141,13 @@ jing j ing jiong j iong jiu j iu ju j v +jv j v juan j van +jvan j van jue j ve +jve j ve jun j vn +jvn j vn ka k a kai k ai kan k an @@ -263,9 +267,13 @@ qing q ing qiong q iong qiu q iu qu q v +qv q v quan q van +qvan q van que q ve +qve q ve qun q vn +qvn q vn ran r an rang r ang rao r ao @@ -356,9 +364,13 @@ xing x ing xiong x iong xiu x iu xu x v +xv x v xuan x van +xvan x van xue x ve +xve x ve xun x vn +xvn x vn ya y a yan y En yang y ang @@ -371,9 +383,13 @@ yo y o yong y ong you y ou yu y v +yv y v yuan y van +yvan y van yue y ve +yve y ve yun y vn +yvn y vn za z a zai z ai zan z an @@ -410,4 +426,4 @@ zu z u zuan z uan zui z ui zun z un -zuo z uo \ No newline at end of file +zuo z uo diff --git a/dictionaries/opencpop.txt b/dictionaries/opencpop.txt index b5bd6468..81656c7f 100644 --- a/dictionaries/opencpop.txt +++ b/dictionaries/opencpop.txt @@ -141,9 +141,13 @@ jing j ing jiong j iong jiu j iu ju j v +jv j v juan j van +jvan j van jue j ve +jve j ve jun j vn +jvn j vn ka k a kai k ai kan k an @@ -263,9 +267,13 @@ qing q ing qiong q iong qiu q iu qu q v +qv q v quan q van +qvan q van que q ve +qve q ve qun q vn +qvn q vn ran r an rang r ang rao r ao @@ -356,9 +364,13 @@ xing x ing xiong x iong xiu x iu xu x v +xv x v xuan x van +xvan x van xue x ve +xve x ve xun x vn +xvn x vn ya y a yan y an yang y ang @@ -371,9 +383,13 @@ yo y o yong y ong you y ou yu y v +yv y v yuan y van +yvan y van yue y ve +yve y ve yun y vn +yvn y vn za z a zai z ai zan z an @@ -410,4 +426,4 @@ zu z u zuan z uan zui z ui zun z un -zuo z uo \ No newline at end of file +zuo z uo diff --git a/docs/README-SVS-custom-phonemes.md b/docs/README-SVS-custom-phonemes.md index 4b8bcf68..c6115ffc 100644 --- a/docs/README-SVS-custom-phonemes.md +++ b/docs/README-SVS-custom-phonemes.md @@ -97,7 +97,7 @@ There are currently two preset dictionaries. #### The original Opencpop dictionary [[source]](../dictionaries/opencpop.txt) -The original Opencpop dictionary, which you can find [here](http://wenet.org.cn/opencpop/resources/annotationformat/), are fully aligned with the standard pinyin format of Mandarin Chinese. We copied the dictionary from the website and removed 5 syllables that has no occurrence in the data labels (`hm`, `hng`, `m`, `n` and `ng`). It has the most compatibility with the previous model weights, but may cause bad cases in pronunciations, especially in cases that the note is a slur. Thus, this dictionary is deprecated by default and remained only for backward compatibility. +The original Opencpop dictionary, which you can find [here](http://wenet.org.cn/opencpop/resources/annotationformat/), are fully aligned with the standard pinyin format of Mandarin Chinese. We copied the dictionary from the website, removed 5 syllables that has no occurrence in the data labels (`hm`, `hng`, `m`, `n` and `ng`) and added some aliases for some syllables (e.g. `jv` for `ju`). It has the most compatibility with the previous model weights, but may cause bad cases in pronunciations, especially in cases that the note is a slur. Thus, this dictionary is deprecated by default and remained only for backward compatibility. Phoneme distribution of Opencpop dataset on this dictionary can be found [here](http://wenet.org.cn/opencpop/resources/statisticalinformation/).