29 lines
1.1 KiB
Python
29 lines
1.1 KiB
Python
import ffmpeg
|
|
import librosa
|
|
import numpy as np
|
|
|
|
|
|
def load_audio(file, sr):
|
|
try:
|
|
# https://github.com/openai/whisper/blob/main/whisper/audio.py#L26
|
|
# This launches a subprocess to decode audio while down-mixing and resampling as necessary.
|
|
# Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
|
|
file = (
|
|
file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
|
|
) # 防止小白拷路径头尾带了空格和"和回车
|
|
out, _ = (
|
|
ffmpeg.input(file, threads=0)
|
|
.output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
|
|
.run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
|
|
)
|
|
return np.frombuffer(out, np.float32).flatten()
|
|
|
|
except AttributeError:
|
|
audio = file[1] / 32768.0
|
|
if len(audio.shape) == 2:
|
|
audio = np.mean(audio, -1)
|
|
return librosa.resample(audio, orig_sr=file[0], target_sr=16000)
|
|
|
|
except Exception as e:
|
|
raise RuntimeError(f"Failed to load audio: {e}")
|