chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix tokenizer is None

Browse Source
This commit is contained in:
Simon
2023-05-20 15:52:45 +02:00
parent 715435db42
commit a1c705b3a7
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
whisperx/asr.py
View File

@ -231,13 +231,16 @@ class FasterWhisperPipeline(Pipeline):
if self.tokenizer is None: if self.tokenizer is None:
language = language or self.detect_language(audio) language = language or self.detect_language(audio)
task = task or "transcribe" task = task or "transcribe"
else:
language = language or self.tokenizer.language_code
task = task or self.tokenizer.task
if task != self.tokenizer.task or language != self.tokenizer.language_code:
self.tokenizer = faster_whisper.tokenizer.Tokenizer(self.model.hf_tokenizer, self.tokenizer = faster_whisper.tokenizer.Tokenizer(self.model.hf_tokenizer,
self.model.model.is_multilingual, task=task, self.model.model.is_multilingual, task=task,
language=language) language=language)
else:
language = language or self.tokenizer.language_code
task = task or self.tokenizer.task
if task != self.tokenizer.task or language != self.tokenizer.language_code:
self.tokenizer = faster_whisper.tokenizer.Tokenizer(self.model.hf_tokenizer,
self.model.model.is_multilingual, task=task,
language=language)
segments: List[SingleSegment] = [] segments: List[SingleSegment] = []
batch_size = batch_size or self._batch_size batch_size = batch_size or self._batch_size