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

v3 init

Browse Source
This commit is contained in:
Max Bain
2023-04-24 21:08:43 +01:00
parent da458863d7
commit 558d980535
11 changed files with 1034 additions and 846 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
whisperx/vad.py
View File

@ -1,22 +1,23 @@
import hashlib
import os
import urllib
import pandas as pd
from typing import Callable, Optional, Text, Union
import numpy as np
import pandas as pd
import torch
import hashlib
from tqdm import tqdm
from typing import Optional, Callable, Union, Text
from pyannote.audio.core.io import AudioFile
from pyannote.core import Annotation, Segment, SlidingWindowFeature
from pyannote.audio.pipelines.utils import PipelineModel
from pyannote.audio import Model
from pyannote.audio.core.io import AudioFile
from pyannote.audio.pipelines import VoiceActivityDetection
from pyannote.audio.pipelines.utils import PipelineModel
from pyannote.core import Annotation, Segment, SlidingWindowFeature
from tqdm import tqdm
from .diarize import Segment as SegmentX
from typing import List, Tuple, Optional
VAD_SEGMENTATION_URL = "https://whisperx.s3.eu-west-2.amazonaws.com/model_weights/segmentation/0b5b3216d60a2d32fc086b47ea8c67589aaeb26b7e07fcbe620d6d0b83e209ea/pytorch_model.bin"
def load_vad_model(device, vad_onset, vad_offset, use_auth_token=None, model_fp=None):
def load_vad_model(device, vad_onset=0.500, vad_offset=0.363, use_auth_token=None, model_fp=None):
model_dir = torch.hub._get_torch_home()
os.makedirs(model_dir, exist_ok = True)
if model_fp is None: