hanfish/LSai

1import ffmpeg
2import numpy as np
3
4
5def load_audio(file, sr):
6    try:
7        # https://github.com/openai/whisper/blob/main/whisper/audio.py#L26
8        # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
9        # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
10        file = (
11            file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
12        )  # 防止小白拷路径头尾带了空格和"和回车
13        out, _ = (
14            ffmpeg.input(file, threads=0)
15            .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
16            .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
17        )
18    except Exception as e:
19        raise RuntimeError(f"Failed to load audio: {e}")
20
21    return np.frombuffer(out, np.float32).flatten()
22