AICoverGen_gradiom / src /my_utils.py
helloWorld199's picture
Upload 2 files
3d15671 verified
import ffmpeg
import numpy as np
import os
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)
)
except Exception as e:
raise RuntimeError(f"Failed to load audio: {e}")
return np.frombuffer(out, np.float32).flatten()
def add_stem_name(path, stemname):
directory, filename_with_ext = os.path.split(path)
filename, extension = os.path.splitext(filename_with_ext)
# Concatenate the stem name with desired suffix and extension
new_filename = f"{filename}{stemname}{extension}"
# Construct the new path
new_path = os.path.join(directory, new_filename)
return new_path