Remove multi language feature (Revert #20)
shirayu opened this issue · 1 comments
shirayu commented
I read the whisper code and noticed that multilingual tokenizer is not supposed in Whisper.
When language
is None
, the tokenizer is not for all languages but for English (en
) for "multilingual whisper models" (tiny, base, small, medium, large).
if multilingual:
tokenizer_name = "multilingual"
task = task or "transcribe"
language = language or "en"
AlexandraRamassamy commented
Hi @shirayu ,
I see you have reverted my PR to fix #23. I understand that the tokenizer does not support a multilanguage mode, however, multilanguage transcription works fine on my end.
I think there is an error in the code you have edited, as language should be None and not opts.language .
Thanks for looking into this :)