r3gm's picture
v0.5.0
b152010
raw
history blame
924 Bytes
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.
file = (
file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
) # To prevent beginners from copying paths with leading or trailing spaces, quotation marks, and line breaks.
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)
)
except Exception as e:
raise RuntimeError(f"Failed to load audio: {e}")
return np.frombuffer(out, np.float32).flatten()