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

Accept alternative VAD methods. Extend to use Silero VAD.

Browse Source
This commit is contained in:
3manifold
2024-09-26 10:28:52 +02:00
parent 10b05fc43f
commit 79eb8fa53d
8 changed files with 262 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
whisperx/transcribe.py
View File

@ -46,6 +46,7 @@ def cli():
parser.add_argument("--return_char_alignments", action='store_true', help="Return character-level alignments in the output json file")
# vad params
parser.add_argument("--vad_method", type=str, default="pyannote", choices=["pyannote", "silero"], help="VAD method to be used")
parser.add_argument("--vad_onset", type=float, default=0.500, help="Onset threshold for VAD (see pyannote.audio), reduce this if speech is not being detected")
parser.add_argument("--vad_offset", type=float, default=0.363, help="Offset threshold for VAD (see pyannote.audio), reduce this if speech is not being detected.")
parser.add_argument("--chunk_size", type=int, default=30, help="Chunk size for merging VAD segments. Default is 30, reduce this if the chunk is too long.")
@ -110,6 +111,7 @@ def cli():
return_char_alignments: bool = args.pop("return_char_alignments")
hf_token: str = args.pop("hf_token")
vad_method: str = args.pop("vad_method")
vad_onset: float = args.pop("vad_onset")
vad_offset: float = args.pop("vad_offset")
@ -175,7 +177,7 @@ def cli():
results = []
tmp_results = []
# model = load_model(model_name, device=device, download_root=model_dir)
model = load_model(model_name, device=device, device_index=device_index, download_root=model_dir, compute_type=compute_type, language=args['language'], asr_options=asr_options, vad_options={"vad_onset": vad_onset, "vad_offset": vad_offset}, task=task, threads=faster_whisper_threads)
model = load_model(model_name, device=device, device_index=device_index, download_root=model_dir, compute_type=compute_type, language=args['language'], asr_options=asr_options, vad_method=vad_method, vad_options={"chunk_size":chunk_size, "vad_onset": vad_onset, "vad_offset": vad_offset}, task=task, threads=faster_whisper_threads)
for audio_path in args.pop("audio"):
audio = load_audio(audio_path)