github/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-03-19 13:28:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: voice length bug in wechaty

Browse Source
This commit is contained in:
lanvent
2023-04-01 21:58:55 +08:00
parent 5badef8ba9
commit dfb2e460b4
2 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
voice/audio_convert.py
View File

@@ -15,7 +15,7 @@ def find_closest_sil_supports(sample_rate):
for rate in sil_supports:
diff = abs(rate - sample_rate)
if diff < mindiff:
closest = sample_rate
closest = rate
mindiff = diff
return closest
@@ -68,8 +68,9 @@ def pcm_to_sil(pcm_path, silk_path):
"""
audio = AudioSegment.from_wav(pcm_path)
wav_data = audio.raw_data
rate = find_closest_sil_supports(audio.frame_rate)
silk_data = pysilk.encode(
wav_data, data_rate=audio.frame_rate, sample_rate=find_closest_sil_supports(audio.frame_rate))
wav_data, data_rate=rate, sample_rate=rate)
with open(silk_path, "wb") as f:
f.write(silk_data)
return audio.duration_seconds * 1000
@@ -82,7 +83,8 @@ def mp3_to_sil(mp3_path, silk_path):
"""
audio = AudioSegment.from_mp3(mp3_path)
wav_data = audio.raw_data
silk_data = pysilk.encode(wav_data, data_rate=audio.frame_rate, sample_rate=find_closest_sil_supports(audio.frame_rate))
rate = find_closest_sil_supports(audio.frame_rate)
silk_data = pysilk.encode(wav_data, data_rate=rate, sample_rate=rate)
# Save the silk file
with open(silk_path, "wb") as f:
f.write(silk_data)