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:
snakers41
2020-12-11 14:23:29 +00:00
parent 80eb5056c9
commit 70047a62bd
2 changed files with 89 additions and 159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

240
silero-vad.ipynb
View File

File diff suppressed because one or more lines are too long

8
utils.py
View File

@@ -195,7 +195,7 @@ class VADiterator:
def state(self, model_out): def state(self, model_out):
current_speech = {} current_speech = {}
for i, predict in enumerate(model_out[:, 1]): for i, predict in enumerate(model_out[:, 1]): # add name
self.buffer.append(predict) self.buffer.append(predict)
if (np.mean(self.buffer) >= self.trig_sum) and not self.triggered: if (np.mean(self.buffer) >= self.trig_sum) and not self.triggered:
self.triggered = True self.triggered = True
@@ -210,7 +210,10 @@ class VADiterator:
return current_speech, self.current_name return current_speech, self.current_name
def state_generator(model, audios, extractor, onnx=False, trig_sum=0.26, neg_trig_sum=0.01, num_steps=8, audios_in_stream=5): def state_generator(model, audios, extractor,
onnx=False,
trig_sum=0.26, neg_trig_sum=0.01,
num_steps=8, audios_in_stream=5):
VADiters = [VADiterator(trig_sum, neg_trig_sum, num_steps) for i in range(audios_in_stream)] VADiters = [VADiterator(trig_sum, neg_trig_sum, num_steps) for i in range(audios_in_stream)]
for i, current_pieces in enumerate(stream_imitator(audios, audios_in_stream)): for i, current_pieces in enumerate(stream_imitator(audios, audios_in_stream)):
for_batch = [x.prepare_batch(*y) for x, y in zip(VADiters, current_pieces)] for_batch = [x.prepare_batch(*y) for x, y in zip(VADiters, current_pieces)]
@@ -264,4 +267,3 @@ def stream_imitator(stereo, audios_in_stream):
return return
values.append((out, wav_name)) values.append((out, wav_name))
yield values yield values