src/my_utils.py

import ffmpeg
import numpy as np
import os
import shutil


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 remove_files_and_folders(folder_path= "/tmp/gradio/"):
    print("Cleaning gradio cache ...")
    try:
        shutil.rmtree(folder_path)
        print(f"All files and folders inside {folder_path} have been removed.")
    except Exception as e:
        print(f"An error occurred: {e}")

def show_stored_files(root_dir):
    for entry in os.listdir(root_dir):
        full_path = os.path.join(root_dir, entry)
        if os.path.isdir(full_path):
            print(f"Directory: {full_path}")
        elif os.path.isfile(full_path):
            print(f"File: {full_path}")