github/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-03-18 12:40:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor(audio_convert.py): remove redundant functions

Browse Source
This commit is contained in:
lanvent
2023-04-20 23:22:08 +08:00
parent 0f8dc91a8b
commit c60f0517fb
1 changed files with 2 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
voice/audio_convert.py
View File

@@ -62,52 +62,14 @@ def any_to_sil(any_path, sil_path):
): ):
shutil.copy2(any_path, sil_path) shutil.copy2(any_path, sil_path)
return 10000 return 10000
if any_path.endswith(".wav"): audio = AudioSegment.from_file(any_path)
return pcm_to_sil(any_path, sil_path)
if any_path.endswith(".mp3"):
return mp3_to_sil(any_path, sil_path)
raise NotImplementedError("Not support file type: {}".format(any_path))
def mp3_to_wav(mp3_path, wav_path):
"""
把mp3格式转成pcm文件
"""
audio = AudioSegment.from_mp3(mp3_path)
audio.export(wav_path, format="wav")
def pcm_to_sil(pcm_path, silk_path):
"""
wav 文件转成 silk
return 声音长度，毫秒
"""
audio = AudioSegment.from_wav(pcm_path)
rate = find_closest_sil_supports(audio.frame_rate) rate = find_closest_sil_supports(audio.frame_rate)
# Convert to PCM_s16 # Convert to PCM_s16
pcm_s16 = audio.set_sample_width(2) pcm_s16 = audio.set_sample_width(2)
pcm_s16 = pcm_s16.set_frame_rate(rate) pcm_s16 = pcm_s16.set_frame_rate(rate)
wav_data = pcm_s16.raw_data 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)
with open(silk_path, "wb") as f: with open(sil_path, "wb") as f:
f.write(silk_data)
return audio.duration_seconds * 1000
def mp3_to_sil(mp3_path, silk_path):
"""
mp3 文件转成 silk
return 声音长度，毫秒
"""
audio = AudioSegment.from_mp3(mp3_path)
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)
# Save the silk file
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