mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2025-01-04 14:05:04 +08:00
17 lines
733 B
Python
17 lines
733 B
Python
import ffmpeg
|
|
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.
|
|
out, _ = (
|
|
ffmpeg.input(file, threads=0)
|
|
.output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=sr)
|
|
.run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
|
|
)
|
|
except Exception as e:
|
|
raise RuntimeError(f"Failed to load audio: {e}")
|
|
|
|
return np.frombuffer(out, np.int16).flatten().astype(np.float32) / 32768.0
|