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

Added vad_filter type

Browse Source
This commit is contained in:
dev-nomi
2023-04-05 17:11:29 +05:00
parent 118e7deedb
commit 4146e56d5b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
whisperx/transcribe.py
View File

@ -44,7 +44,7 @@ def cli():
parser.add_argument("--no_align", action='store_true', help="Do not perform phoneme alignment")
# vad params
parser.add_argument("--vad_filter", default=True, help="Whether to pre-segment audio with VAD, highly recommended! Produces more accurate alignment + timestamp see WhisperX paper https://arxiv.org/abs/2303.00747")
parser.add_argument("--vad_filter", type=str2bool, default=True, help="Whether to pre-segment audio with VAD, highly recommended! Produces more accurate alignment + timestamp see WhisperX paper https://arxiv.org/abs/2303.00747")
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.")