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 'v3' of https://github.com/m-bain/whisperX into v3

Browse Source 
Conflicts:
	whisperx/asr.py
This commit is contained in:
Max Bain
2023-06-05 15:30:02 +01:00
parent a323cff654 ec6a110cdf
commit b026407fd9
6 changed files with 131 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
whisperx/transcribe.py
View File

@ -21,6 +21,7 @@ def cli():
parser.add_argument("--model", default="small", help="name of the Whisper model to use")
parser.add_argument("--model_dir", type=str, default=None, help="the path to save model files; uses ~/.cache/whisper by default")
parser.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu", help="device to use for PyTorch inference")
parser.add_argument("--device_index", default=0, type=int, help="device index to use for FasterWhisper inference")
parser.add_argument("--batch_size", default=8, type=int, help="device to use for PyTorch inference")
parser.add_argument("--compute_type", default="float16", type=str, choices=["float16", "float32", "int8"], help="compute type for computation")
@ -80,6 +81,7 @@ def cli():
output_dir: str = args.pop("output_dir")
output_format: str = args.pop("output_format")
device: str = args.pop("device")
device_index: int = args.pop("device_index")
compute_type: str = args.pop("compute_type")
# model_flush: bool = args.pop("model_flush")
@ -148,7 +150,7 @@ def cli():
results = []
tmp_results = []
# model = load_model(model_name, device=device, download_root=model_dir)
model = load_model(model_name, device=device, compute_type=compute_type, language=args['language'], asr_options=asr_options, vad_options={"vad_onset": vad_onset, "vad_offset": vad_offset}, task=task)
model = load_model(model_name, device=device, device_index=device_index, compute_type=compute_type, language=args['language'], asr_options=asr_options, vad_options={"vad_onset": vad_onset, "vad_offset": vad_offset}, task=task)
for audio_path in args.pop("audio"):
audio = load_audio(audio_path)