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

Update transcribe.py

Browse Source 
added the ability to include HF access token in order to use PyAnnote models
This commit is contained in:
Mahmoud Ashraf
2023-01-26 00:42:35 +02:00
committed by GitHub
parent 6b2aa4ff3e
commit e7773358a3
1 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
whisperx/transcribe.py
View File

@ -385,6 +385,7 @@ def cli():
parser.add_argument("--logprob_threshold", type=optional_float, default=-1.0, help="if the average log probability is lower than this value, treat the decoding as failed") parser.add_argument("--logprob_threshold", type=optional_float, default=-1.0, help="if the average log probability is lower than this value, treat the decoding as failed")
parser.add_argument("--no_speech_threshold", type=optional_float, default=0.6, help="if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence") parser.add_argument("--no_speech_threshold", type=optional_float, default=0.6, help="if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence")
parser.add_argument("--threads", type=optional_int, default=0, help="number of threads used by torch for CPU inference; supercedes MKL_NUM_THREADS/OMP_NUM_THREADS") parser.add_argument("--threads", type=optional_int, default=0, help="number of threads used by torch for CPU inference; supercedes MKL_NUM_THREADS/OMP_NUM_THREADS")
parser.add_argument("--hf_token", type=str, default=None, help="Hugging Face Access Token to access PyAnnote gated models")
args = parser.parse_args().__dict__ args = parser.parse_args().__dict__
model_name: str = args.pop("model") model_name: str = args.pop("model")
@ -398,6 +399,7 @@ def cli():
align_from_prev: bool = args.pop("align_from_prev") align_from_prev: bool = args.pop("align_from_prev")
interpolate_method: bool = args.pop("interpolate_method") interpolate_method: bool = args.pop("interpolate_method")
hf_token: str = args.pop("hf_token")
vad_filter: bool = args.pop("vad_filter") vad_filter: bool = args.pop("vad_filter")
vad_input: bool = args.pop("vad_input") vad_input: bool = args.pop("vad_input")
@ -410,12 +412,14 @@ def cli():
vad_input = pd.read_csv(vad_input, header=None, sep= " ") vad_input = pd.read_csv(vad_input, header=None, sep= " ")
elif vad_filter: elif vad_filter:
from pyannote.audio import Pipeline from pyannote.audio import Pipeline
vad_pipeline = Pipeline.from_pretrained("pyannote/voice-activity-detection") vad_pipeline = Pipeline.from_pretrained("pyannote/voice-activity-detection",
use_auth_token=hf_token)
diarize_pipeline = None diarize_pipeline = None
if diarize: if diarize:
from pyannote.audio import Pipeline from pyannote.audio import Pipeline
diarize_pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization@2.1") diarize_pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization@2.1",
use_auth_token=hf_token)
os.makedirs(output_dir, exist_ok=True) os.makedirs(output_dir, exist_ok=True)