Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-23 22:15:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

formatting fix

Browse Source
This commit is contained in:
Jong Wook Kim 2023-11-06 10:09:38 -08:00
parent 4aa8014589
commit 0efe52add2
3 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
whisper/__init__.py
View File

@ -42,8 +42,8 @@ _ALIGNMENT_HEADS = {
"medium": b"ABzY8B0Jh+0{>%R7}kK1fFL7w6%<-Pf*t^=N)Qr&0RR9",
"large-v1": b"ABzY8r9j$a0{>%R7#4sLmoOs{s)o3~84-RPdcFk!JR<kSfC2yj",
"large-v2": b"ABzY8zd+h!0{>%R7=D0pU<_bnWW*tkYAhobTNnu$jnkEkXqp)j;w1Tzk)UH3X%SZd&fFZ2fC2yj",
"large-v3": b'ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00',
"large": b'ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00',
"large-v3": b"ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00",
"large": b"ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00",
}

4
whisper/decoding.py
View File

@ -32,7 +32,9 @@ def detect_language(
list of dictionaries containing the probability distribution over all languages.
"""
if tokenizer is None:
tokenizer = get_tokenizer(model.is_multilingual, num_languages=model.num_languages)
tokenizer = get_tokenizer(
model.is_multilingual, num_languages=model.num_languages
)
if (
tokenizer.language is None
or tokenizer.language_token not in tokenizer.sot_sequence

8
whisper/tokenizer.py
View File

@ -251,7 +251,9 @@ class Tokenizer:
keeping basic punctuations like commas, periods, question marks, exclamation points, etc.
"""
symbols = list('"#()*+/:;<=>@[\\]^_`{|}~「」『』')
symbols += "<< >> <<< >>> -- --- -( -[ (' (\" (( )) ((( ))) [[ ]] {{ }} ♪♪ ♪♪♪".split()
symbols += (
"<< >> <<< >>> -- --- -( -[ (' (\" (( )) ((( ))) [[ ]] {{ }} ♪♪ ♪♪♪".split()
)
# symbols that may be a single token or multiple tokens depending on the tokenizer.
# In case they're multiple tokens, suppress the first token, which is safe because:
@ -388,4 +390,6 @@ def get_tokenizer(
encoding = get_encoding(name=encoding_name, num_languages=num_languages)
return Tokenizer(encoding=encoding, num_languages=num_languages, language=language, task=task)
return Tokenizer(
encoding=encoding, num_languages=num_languages, language=language, task=task
)