MycroftAI
/
mycroft-precise
mirror of https://github.com/MycroftAI/mycroft-precise.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Fix major bug in precise-train-incremental 

Previously it wouldn't update its own buffer so the files it would save would be mostly silence
pull/10/head
Matthew D. Scholefield 2018-04-18 17:52:09 -05:00
parent 755af134f6
commit a3274b8d33
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
precise/scripts/train_incremental.py
View File

@ -127,14 +127,14 @@ class IncrementalTrainer:
for i, chunk in enumerate(chunk_audio(audio, self.args.chunk_size)):
print('\r' + str(i * 100. / num_chunks) + '%', end='', flush=True)
audio_buffer = np.concatenate((self.audio_buffer[len(chunk):], chunk))
self.audio_buffer = np.concatenate((self.audio_buffer[len(chunk):], chunk))
conf = self.listener.update(chunk)
if conf > 0.5:
samples_since_train += 1
name = splitext(basename(fn))[0] + '-' + str(i) + '.wav'
name = join(self.args.folder, 'test' if save_test else '', 'not-wake-word',
'generated', name)
save_audio(name, audio_buffer)
save_audio(name, self.audio_buffer)
print()
print('Saved to:', name)