deepgeek/silero-vad
2
0
Fork 0
mirror of https://github.com/snakers4/silero-vad.git synced 2026-02-05 18:09:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

fx

Browse Source
This commit is contained in:
adamnsandle
2020-12-15 12:34:51 +00:00
parent 557a32ed1b
commit d5a30a8664
2 changed files with 23 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
hubconf.py
View File

@@ -1,11 +1,13 @@
dependencies = ['torch', 'omegaconf', 'torchaudio'] dependencies = ['torch', 'torchaudio', 'numpy']
import torch import torch
from omegaconf import OmegaConf from omegaconf import OmegaConf
from utils import (init_jit_model, from utils import (init_jit_model,
read_audio, get_speech_ts,
read_batch, save_audio,
split_into_batches, read_audio,
prepare_model_input) state_generator,
single_audio_stream,
collect_speeches)
def silero_stt(**kwargs): def silero_stt(**kwargs):
@@ -13,16 +15,15 @@ def silero_stt(**kwargs):
Returns a model and a set of utils Returns a model and a set of utils
Please see https://github.com/snakers4/silero-vad for usage examples Please see https://github.com/snakers4/silero-vad for usage examples
""" """
torch.hub.download_url_to_file('https://raw.githubusercontent.com/snakers4/silero-vad/master/models.yml', torch.hub.download_url_to_file('https://raw.githubusercontent.com/snakers4/silero-vad/master/files/model.jit',
'silero_vad_models.yml', 'files/model.jit',
progress=False) progress=False)
models = OmegaConf.load('silero_vad_models.yml') model = init_jit_model(model_url='files/model.jit')
utils = (get_speech_ts,
model = init_jit_model(model_url=models.latest.jit, save_audio,
**kwargs) read_audio,
utils = (read_batch, state_generator,
split_into_batches, single_audio_stream,
read_audio, collect_speeches)
prepare_model_input)
return model, utils return model, utils

6
utils.py
View File

@@ -224,3 +224,9 @@ def single_audio_stream(model, audio, onnx=False, trig_sum=0.26,
if state[0]: if state[0]:
states.append(state[0]) states.append(state[0])
yield states yield states
def collect_speeches(tss, wav):
speech_chunks = []
for i in tss:
speech_chunks.append(wav[i['start']: i['end']])
return torch.cat(speech_chunks)