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

Merge branch 'main' into add-merge-chunk-size-as-argument

Browse Source
This commit is contained in:
Max Bain
2023-08-29 10:05:05 -06:00
committed by GitHub
parent eb771cf56d a8bfac6bef
commit 9647f60fca
5 changed files with 30 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
whisperx/asr.py
View File

@ -247,7 +247,7 @@ class FasterWhisperPipeline(Pipeline):
return final_iterator
def transcribe(
self, audio: Union[str, np.ndarray], batch_size=None, num_workers=0, language=None, task=None, chunk_size=30
self, audio: Union[str, np.ndarray], batch_size=None, num_workers=0, language=None, task=None, chunk_size=30, print_progress = False, combined_progress=False
) -> TranscriptionResult:
if isinstance(audio, str):
audio = load_audio(audio)
@ -285,7 +285,12 @@ class FasterWhisperPipeline(Pipeline):
segments: List[SingleSegment] = []
batch_size = batch_size or self._batch_size
total_segments = len(vad_segments)
for idx, out in enumerate(self.__call__(data(audio, vad_segments), batch_size=batch_size, num_workers=num_workers)):
if print_progress:
base_progress = ((idx + 1) / total_segments) * 100
percent_complete = base_progress / 2 if combined_progress else base_progress
print(f"Progress: {percent_complete:.2f}%...")
text = out['text']
if batch_size in [0, 1, None]:
text = text[0]