kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-07-20 21:57:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add convert pcm32 to pcm16

Browse Source
This commit is contained in:
lanvent
2023-04-03 22:55:39 +08:00
parent b74274b96b
commit acddadc406
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
voice/audio_convert.py
View File

@@ -67,23 +67,28 @@ def pcm_to_sil(pcm_path, silk_path):
return 声音长度，毫秒 return 声音长度，毫秒
""" """
audio = AudioSegment.from_wav(pcm_path) audio = AudioSegment.from_wav(pcm_path)
wav_data = audio.raw_data
rate = find_closest_sil_supports(audio.frame_rate) rate = find_closest_sil_supports(audio.frame_rate)
# Convert to PCM_s16
pcm_s16 = audio.set_sample_width(2)
pcm_s16 = pcm_s16.set_frame_rate(rate)
wav_data = pcm_s16.raw_data
silk_data = pysilk.encode( silk_data = pysilk.encode(
wav_data, data_rate=rate, sample_rate=rate) wav_data, data_rate=rate, sample_rate=rate)
with open(silk_path, "wb") as f: with open(silk_path, "wb") as f:
f.write(silk_data) f.write(silk_data)
return audio.duration_seconds * 1000 return audio.duration_seconds * 1000
def mp3_to_sil(mp3_path, silk_path): def mp3_to_sil(mp3_path, silk_path):
""" """
mp3 文件转成 silk mp3 文件转成 silk
return 声音长度，毫秒 return 声音长度，毫秒
""" """
audio = AudioSegment.from_mp3(mp3_path) audio = AudioSegment.from_mp3(mp3_path)
wav_data = audio.raw_data
rate = find_closest_sil_supports(audio.frame_rate) rate = find_closest_sil_supports(audio.frame_rate)
# Convert to PCM_s16
pcm_s16 = audio.set_sample_width(2)
pcm_s16 = pcm_s16.set_frame_rate(rate)
wav_data = pcm_s16.raw_data
silk_data = pysilk.encode(wav_data, data_rate=rate, sample_rate=rate) silk_data = pysilk.encode(wav_data, data_rate=rate, sample_rate=rate)
# Save the silk file # Save the silk file
with open(silk_path, "wb") as f: with open(silk_path, "wb") as f: