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

feat: add verbose output (#759)

Browse Source 
---------

Co-authored-by: Abhishek Sharma <abhishek@zipteams.com>
Co-authored-by: Barabazs <31799121+Barabazs@users.noreply.github.com>
This commit is contained in:
Abhishek Sharma
2025-01-01 17:37:52 +05:30
committed by GitHub
parent 15ad5bf7df
commit 51da22771f
2 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
whisperx/asr.py
View File

@ -171,7 +171,7 @@ 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, print_progress = False, combined_progress=False
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, verbose=False
) -> TranscriptionResult:
if isinstance(audio, str):
audio = load_audio(audio)
@ -223,6 +223,8 @@ class FasterWhisperPipeline(Pipeline):
text = out['text']
if batch_size in [0, 1, None]:
text = text[0]
if verbose:
print(f"Transcript: [{round(vad_segments[idx]['start'], 3)} --> {round(vad_segments[idx]['end'], 3)}] {text}")
segments.append(
{
"text": text,

3
whisperx/transcribe.py
View File

@ -87,6 +87,7 @@ def cli():
device: str = args.pop("device")
device_index: int = args.pop("device_index")
compute_type: str = args.pop("compute_type")
verbose: bool = args.pop("verbose")
# model_flush: bool = args.pop("model_flush")
os.makedirs(output_dir, exist_ok=True)
@ -173,7 +174,7 @@ def cli():
audio = load_audio(audio_path)
# >> VAD & ASR
print(">>Performing transcription...")
result = model.transcribe(audio, batch_size=batch_size, chunk_size=chunk_size, print_progress=print_progress)
result = model.transcribe(audio, batch_size=batch_size, chunk_size=chunk_size, print_progress=print_progress, verbose=verbose)
results.append((result, audio_path))
# Unload Whisper and VAD