mrq/vall-e
5
9
Fork 0
Code Issues 8 Pull Requests Packages Projects Releases Wiki Activity

fix oversight with phonemizing french because espeak defines french as fr-fr instead of fr (even though spain spanish is es and not es-sp or some shit, but portugal portuguese is pt-pt)

Browse Source
This commit is contained in:
mrq 2024-09-13 12:53:36 -05:00
parent 4f3c7a37c8
commit 69f140ba45
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
vall_e/emb/g2p.py
View File

@ -26,6 +26,15 @@ def romanize( runes, sep="" ):
result = kks.convert( runes ) result = kks.convert( runes )
return sep.join([ res['hira'] for res in result ]) return sep.join([ res['hira'] for res in result ])
# to-do: fill out this table
# although desu the only thing that might be needed are en-uk/en-gb, es-la, pt-br, and pt-pt
def coerce_language( lang ):
if lang == "en":
lang = "en-us"
if lang == "fr":
return "fr-fr"
return lang
cached_backends = {} cached_backends = {}
def _get_backend( language="en-us", backend="espeak", punctuation=True, stress=True, strip=True ): def _get_backend( language="en-us", backend="espeak", punctuation=True, stress=True, strip=True ):
key = f'{language}_{backend}' key = f'{language}_{backend}'
@ -44,8 +53,7 @@ def _get_backend( language="en-us", backend="espeak", punctuation=True, stress=T
def encode(text: str, language="en-us", backend="auto", punctuation=True, stress=True, strip=True) -> list[str]: def encode(text: str, language="en-us", backend="auto", punctuation=True, stress=True, strip=True) -> list[str]:
if language == "en": language = coerce_language( language )
language = "en-us"
# Convert to kana because espeak does not like kanji... # Convert to kana because espeak does not like kanji...
if language[:2] == "ja" and backend == "auto": if language[:2] == "ja" and backend == "auto":