通过视频提取音频

ffmpeg -i D:/ai-test/image_video.mp4 -vn -acodec pcm_s16le -ar 16000 -ac 1 D:/ai-test/output.wav

生成字幕文件

docker run -it \
>   -v /opt/sound/models:/models \
>   -v /opt/sound/audios:/audios \
>   ghcr.io/ggerganov/whisper.cpp:main "./build/bin/whisper-cli -m /models/ggml-base.bin -l zh -osrt -f /audios/output.wav"

合并字幕

cd d:/ai-test
ffmpeg -i  image_video.mp4 -lavfi "subtitles=output.wav.srt:force_style='Alignment=2,MarginV=5'" -y output_with_subtitle.mp4