Merge pull request #20 from snakers4/adamnsandle

Adamnsandle

README.md

@@ -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)
 - `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));
+- `min_speech_samples` - minimum speech chunk duration in samples
 
 ### How VAD Works
 

utils.py

@@ -59,6 +59,7 @@ def get_speech_ts(wav: torch.Tensor,
                   num_steps: int = 8,
                   batch_size: int = 200,
                   num_samples_per_window: int = 4000,
+                  min_speech_samples: int = 10000, #samples
                   run_function=validate):
 
     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)
         if ((sum(buffer) / len(buffer)) < neg_trig_sum) and triggered:
             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)
             current_speech = {}
             triggered = False