|
- import os
- import av
- import pilk
-
- def silk_to_pcm(silk_path: str, pcm_path: str) -> int:
- """将silk文件转为pcm文件"""
- pcm_rate = pilk.decode(silk_path, pcm_path)
- return pcm_rate
-
- def to_pcm(in_path: str) -> tuple[str, int]:
- """任意媒体文件转 pcm"""
- if in_path.endswith('.silk'):
- pcm_path = os.path.splitext(in_path)[0] + '.pcm'
- sample_rate = silk_to_pcm(in_path, pcm_path)
- else:
- out_path = os.path.splitext(in_path)[0] + '.pcm'
- with av.open(in_path) as in_container:
- in_stream = in_container.streams.audio[0]
- sample_rate = in_stream.codec_context.sample_rate
- with av.open(out_path, 'w', 's16le') as out_container:
- out_stream = out_container.add_stream(
- 'pcm_s16le',
- rate=sample_rate,
- layout='mono'
- )
- try:
- for frame in in_container.decode(in_stream):
- frame.pts = None
- for packet in out_stream.encode(frame):
- out_container.mux(packet)
- except:
- pass
- pcm_path = out_path
- return pcm_path, sample_rate
-
-
- def convert_to_silk(media_path: str) -> str:
- """任意媒体文件转 silk, 返回silk路径"""
- pcm_path, sample_rate = to_pcm(media_path)
- silk_path = os.path.splitext(pcm_path)[0] + '.silk'
- pilk.encode(pcm_path, silk_path, pcm_rate=sample_rate, tencent=True)
- os.remove(pcm_path)
- return silk_path
|
