Skip to content

Commit

Permalink
Add syllable aliases
Browse files Browse the repository at this point in the history
  • Loading branch information
yqzhishen committed Nov 30, 2022
1 parent e8d4134 commit 4d04ae1
Show file tree
Hide file tree
Showing 4 changed files with 36 additions and 3 deletions.
1 change: 1 addition & 0 deletions dictionaries/.gitignore
Original file line number Diff line number Diff line change
@@ -1,2 +1,3 @@
*.py
*.txt
!opencpop*
18 changes: 17 additions & 1 deletion dictionaries/opencpop-strict.txt
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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
Expand Down Expand Up @@ -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
Expand All @@ -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
Expand Down Expand Up @@ -410,4 +426,4 @@ zu z u
zuan z uan
zui z ui
zun z un
zuo z uo
zuo z uo
18 changes: 17 additions & 1 deletion dictionaries/opencpop.txt
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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
Expand Down Expand Up @@ -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
Expand All @@ -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
Expand Down Expand Up @@ -410,4 +426,4 @@ zu z u
zuan z uan
zui z ui
zun z un
zuo z uo
zuo z uo
2 changes: 1 addition & 1 deletion docs/README-SVS-custom-phonemes.md
Original file line number Diff line number Diff line change
Expand Up @@ -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/).

Expand Down

0 comments on commit 4d04ae1

Please sign in to comment.