0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

文字起こしモデル Whisperの実行Libraryまとめ

Last updated at Posted at 2024-12-07

Whisper (Official)

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg
pip install -U openai-whisper

whisper audio.flac audio.mp3 audio.wav --model turbo

faster-whisper (処理速度が最大4倍改善。)

# Unlike openai-whisper, FFmpeg does not need to be installed on the system. The audio is decoded with the Python library PyAV which bundles the FFmpeg libraries in its package.
# 翻訳: openai-whisperとは異なり、FFmpegをシステムにインストールする必要はありません。音声は、FFmpegライブラリをパッケージにバンドルしたPythonライブラリPyAVでデコードされます。

pip install faster-whisper
# CLIは標準サポートしてない   検索すると別repoで見つかる

mlx-whisper (AppleSilicon向け。MLXを使ったもの。早いらしい。)

# on macOS using Homebrew (https://brew.sh/)
brew install ffmpeg
pip install mlx-whisper

mlx_whisper audio_file.mp3

lightning-whisper-mlx (一番早いらしい。日本語で試したけど対応してないのか、ダメだった。)

image.png
https://github.com/mustafaaljadery/lightning-whisper-mlx/blob/main/speed_image.png

pip install lightning-whisper-mlx

# CLIは標準サポートしてない

Whisper.cpp (C/C++でPortingしたもの。比較がないので速度は不明。いろんなデバイスでWhisper動かしたい人向けかも)

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?