FFmpeg × Whisperで自動字幕を生成する

pip install openai-whisper

ffmpeg -i input.mp4 -vn -acodec pcm_s16le -ar 16000 -ac 1 audio.wav

whisper audio.wav --model medium --language ja --output_format srt --output_dir ./subtitles

1
00:00:00,000 --> 00:00:03,500
こんにちは、今日はFFmpegとWhisperの使い方を紹介します。

2
00:00:03,500 --> 00:00:07,200
まずはWhisperのインストールから始めましょう。

import whisper

model = whisper.load_model("medium")
result = model.transcribe("audio.wav", language="ja")

# SRT形式で保存する
def format_timestamp(seconds: float) -> str:
    ms = int((seconds % 1) * 1000)
    s = int(seconds) % 60
    m = int(seconds) // 60 % 60
    h = int(seconds) // 3600
    return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}"

with open("subtitles/audio.srt", "w", encoding="utf-8") as f:
    for i, segment in enumerate(result["segments"], start=1):
        start = format_timestamp(segment["start"])
        end = format_timestamp(segment["end"])
        text = segment["text"].strip()
        f.write(f"{i}\n{start} --> {end}\n{text}\n\n")

print("SRT ファイルを生成しました")

ffmpeg -i input.mp4 -vf "subtitles=subtitles/audio.srt" -c:a copy output.mp4

ffmpeg -i input.mp4 \
  -vf "subtitles=subtitles/audio.srt:force_style='FontName=Noto Sans CJK JP,FontSize=24,PrimaryColour=&HFFFFFF&,OutlineColour=&H000000&,Outline=2'" \
  -c:a copy output.mp4

import subprocess
import sys
import os
import whisper


def extract_audio(input_video: str, output_audio: str) -> None:
    """動画から音声を抽出する"""
    cmd = [
        "ffmpeg", "-i", input_video,
        "-vn", "-acodec", "pcm_s16le",
        "-ar", "16000", "-ac", "1",
        output_audio, "-y"
    ]
    subprocess.run(cmd, check=True, capture_output=True)
    print(f"音声を抽出しました: {output_audio}")


def transcribe_to_srt(audio_path: str, srt_path: str, model_name: str = "medium") -> None:
    """Whisper で文字起こしして SRT を生成する"""
    model = whisper.load_model(model_name)
    result = model.transcribe(audio_path, language="ja")

    def format_timestamp(seconds: float) -> str:
        ms = int((seconds % 1) * 1000)
        s = int(seconds) % 60
        m = int(seconds) // 60 % 60
        h = int(seconds) // 3600
        return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}"

    with open(srt_path, "w", encoding="utf-8") as f:
        for i, segment in enumerate(result["segments"], start=1):
            start = format_timestamp(segment["start"])
            end = format_timestamp(segment["end"])
            text = segment["text"].strip()
            f.write(f"{i}\n{start} --> {end}\n{text}\n\n")

    print(f"SRT を生成しました: {srt_path}")


def burn_subtitles(input_video: str, srt_path: str, output_video: str) -> None:
    """字幕を動画に焼き込む"""
    # パスに非ASCII文字が含まれないことを前提とする
    vf = f"subtitles={srt_path}"
    cmd = [
        "ffmpeg", "-i", input_video,
        "-vf", vf,
        "-c:a", "copy",
        output_video, "-y"
    ]
    subprocess.run(cmd, check=True, capture_output=True)
    print(f"字幕焼き込み完了: {output_video}")


def main(input_video: str) -> None:
    base = os.path.splitext(input_video)[0]
    audio_path = f"{base}_audio.wav"
    srt_path = f"{base}_subtitles.srt"
    output_video = f"{base}_subtitled.mp4"

    print("=== 字幕自動生成パイプライン ===")
    extract_audio(input_video, audio_path)
    transcribe_to_srt(audio_path, srt_path)
    burn_subtitles(input_video, srt_path, output_video)

    # 中間ファイルを削除する
    os.remove(audio_path)
    print(f"\n完了: {output_video}")


if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("使い方: python subtitle_pipeline.py <input_video>")
        sys.exit(1)
    main(sys.argv[1])

python subtitle_pipeline.py input.mp4

pip install faster-whisper

from faster_whisper import WhisperModel

model = WhisperModel("turbo", compute_type="float16")
segments, info = model.transcribe("audio.wav", language="ja")

with open("subtitles/audio.srt", "w", encoding="utf-8") as f:
    for i, segment in enumerate(segments, start=1):
        start = format_timestamp(segment.start)
        end = format_timestamp(segment.end)
        f.write(f"{i}\n{start} --> {end}\n{segment.text.strip()}\n\n")