GitHub - openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert

[efcl]

音声ファイルから文字起こし、翻訳ができるツール。 大規模なデータセットでトレーニングしていて、日本語を含む色々な言語に対応している

[razokulover]

あとで試す

[aknyonaka]

使うかもしれないからブクマしとこ…

[busylog]

5gb VRAM for medium

[nilab]

"Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification."

[zakinco]

これはすごい。メモ。／dockerで簡単に動く。文字起こし楽になるわ。

[barlog]

ｈっｍ