Whisper 语音转文字：CUDA 与 Apple Silicon 尝试

pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple ## 清华源
pip install -U openai-whisper #安装pypi包（这个缺少tiktoken
pip install git+https://github.com/openai/whisper.git  #安装最新更新以及依赖
pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git #更新用这个

# on Ubuntu or Debian
sudo apt update && sudo apt install ffmpeg

# on Arch Linux
sudo pacman -S ffmpeg

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg

# on Windows using Chocolatey (https://chocolatey.org/)
choco install ffmpeg

# on Windows using Scoop (https://scoop.sh/)
scoop install ffmpeg

(base) ubuntu@ip-10-0-29-42:~$ time whisper 1.mp4 --model large

def remove_timestamps_and_empty_lines(input_file_path, output_file_path):
    # Read the file
    with open(input_file_path, "r", encoding="utf-8") as file:
        lines = file.readlines()

    # Remove the timestamp from each line and filter out empty lines
    cleaned_lines = [
        line.strip().split("] ", 1)[-1].strip()  # Split and remove the timestamp
        for line in lines if "] " in line and line.strip().split("] ", 1)[-1].strip()  # Check if there is text after removing timestamp
    ]

    # Write the cleaned, non-empty lines to a new file
    with open(output_file_path, "w", encoding="utf-8") as file:
        file.write("，".join(cleaned_lines))

# Example usage
input_file_path = '1.txt'  # Specify the path to your input file
output_file_path = '2.txt'  # Specify the path to your output file

remove_timestamps_and_empty_lines(input_file_path, output_file_path)

# Install Python dependencies needed for the creation of the Core ML model:
pip install ane_transformers
pip install openai-whisper
pip install coremltools


# using Makefile
make clean
WHISPER_COREML=1 make -j

### 下载模型
make base
### Generate a Core ML model.
./models/generate-coreml-model.sh base

# This will generate the folder models/ggml-base.en-encoder.mlmodelc  

# 先用ffmpeg转码
ffmpeg -i 1.mp4 -ar 16000 -ac 1 output.wav

# 执行ggml-{model}.bin
time ./main -m models/ggml-base.bin -l zh -osrt -f 'output.wav'

import os
import subprocess
import ffmpeg


def convert_to_wav(source_file, target_file):
    """使用 ffmpeg 将音频或视频文件转换为 WAV 格式，自动覆盖现有文件。"""
    ffmpeg.input(source_file).output(target_file, ar='16000', ac=1).global_args('-y').run()


def process_audio_with_main(audio_file, output_dir):
    """使用 main 程序处理音频文件并提取文字到指定目录。"""
    audio_base_name = os.path.basename(audio_file)
    # output_file = os.path.join(output_dir, audio_base_name.replace('.wav', '.vtt'))
    command = [
        '/Desktop/whisper.cpp/main',  # 程序名
        '-m', '/Users/Desktop/whisper.cpp/models/ggml-large-v3.bin',  # 模型文件路径
        '-l', 'zh',  # 语言选项
        '-osrt',  # 输出选项
        '-f', audio_file,
        '-of', f'{output_dir}/{audio_base_name}',  # 输入文件参数
        '-otxt'  # 输出文件参数
    ]
    print(command)
    subprocess.run(command)


def ensure_dir(directory):
    """确保目录存在，如果不存在则创建它。"""
    if not os.path.exists(directory):
        os.makedirs(directory)


def find_and_process_files(directory):
    """遍历目录，查找所有 MP3 和 MP4 文件，转换并处理它们。"""
    wav_dir = os.path.join(directory, 'wav')
    vtt_dir = os.path.join(directory, 'vtt')
    ensure_dir(wav_dir)
    ensure_dir(vtt_dir)

    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith(('.mp3', '.mp4')):
                full_path = os.path.join(root, file)
                print(full_path)
                wav_path = os.path.join(wav_dir, os.path.splitext(file)[0] + '.wav')
                print(f"Converting {full_path} to {wav_path}")
                convert_to_wav(full_path, wav_path)
                print(f"Processing {wav_path}")
                print("1", wav_path, "0", vtt_dir)
                process_audio_with_main(wav_path, vtt_dir)


# 指定需要遍历的文件夹路径
directory_path = '/Desktop/dy'
find_and_process_files(directory_path)