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

Merge pull request #20 from snakers4/adamnsandle

Browse Source 
Adamnsandle
This commit is contained in:
Alexander Veysov
2021-01-26 16:10:17 +03:00
committed by GitHub
parent e4b7006fee 5a7028ebfe
commit ad53eb9161
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -322,6 +322,7 @@ Since our VAD (only VAD, other networks are more flexible) was trained on chunks
- `neg_trig_sum` - same as `trig_sum`, but for switching from triggered to non-triggered state (non-speech) - `neg_trig_sum` - same as `trig_sum`, but for switching from triggered to non-triggered state (non-speech)
- `num_steps` - nubmer of overlapping windows to split audio chunk into (we recommend 4 or 8) - `num_steps` - nubmer of overlapping windows to split audio chunk into (we recommend 4 or 8)
- `num_samples_per_window` - number of samples in each window, our models were trained using `4000` samples (250 ms) per window, so this is preferable value (lesser values reduce [quality](https://github.com/snakers4/silero-vad/issues/2#issuecomment-750840434)); - `num_samples_per_window` - number of samples in each window, our models were trained using `4000` samples (250 ms) per window, so this is preferable value (lesser values reduce [quality](https://github.com/snakers4/silero-vad/issues/2#issuecomment-750840434));
- `min_speech_samples` - minimum speech chunk duration in samples
### How VAD Works ### How VAD Works

3
utils.py
View File

@@ -59,6 +59,7 @@ def get_speech_ts(wav: torch.Tensor,
num_steps: int = 8, num_steps: int = 8,
batch_size: int = 200, batch_size: int = 200,
num_samples_per_window: int = 4000, num_samples_per_window: int = 4000,
min_speech_samples: int = 10000, #samples
run_function=validate): run_function=validate):
num_samples = num_samples_per_window num_samples = num_samples_per_window
@@ -97,7 +98,7 @@ def get_speech_ts(wav: torch.Tensor,
current_speech['start'] = step * max(0, i-num_steps) current_speech['start'] = step * max(0, i-num_steps)
if ((sum(buffer) / len(buffer)) < neg_trig_sum) and triggered: if ((sum(buffer) / len(buffer)) < neg_trig_sum) and triggered:
current_speech['end'] = step * i current_speech['end'] = step * i
if (current_speech['end'] - current_speech['start']) > 10000: if (current_speech['end'] - current_speech['start']) > min_speech_samples:
speeches.append(current_speech) speeches.append(current_speech)
current_speech = {} current_speech = {}
triggered = False triggered = False