yumoqing/rtcllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bugfix

Browse Source
This commit is contained in:
yumoqing 2024-09-14 17:22:15 +08:00
parent 9ea44d5a5d
commit 7d4cf9c494
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
rtcllm/vad.py
View File

@ -136,6 +136,7 @@ class AudioTrackVad(MediaStreamTrack):
Takes path, PCM audio data, and sample rate. Takes path, PCM audio data, and sample rate.
""" """
"""
audio_data = self.to_mono16000_data() audio_data = self.to_mono16000_data()
path = temp_file(suffix='.wav') path = temp_file(suffix='.wav')
# print(f'temp_file={path}') # print(f'temp_file={path}')
@ -150,4 +151,17 @@ class AudioTrackVad(MediaStreamTrack):
if self.onvoiceend: if self.onvoiceend:
await self.onvoiceend(path) await self.onvoiceend(path)
# print('************over*******') # print('************over*******')
return
"""
path = temp_file(suffix='.wav')
output_container = av.open(path, 'w')
out_stream = output_container.add_stream('pcm_s16le', rate=16000, layout='mono')
resampler = AudioResampler(format=out_stream.format, layout=out_stream.layout, rate=out_stream.rate)
for frame in self.voiced_frames:
for f in resampler.resample(frame):
output_container.mux(out_stream.encode(frame))
output_container.mux(out_stream.encode())
output_container.close()
return path