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.
世界ランキング
#76 4
国家ランキング
113 5
カテゴリレベル
6
アクセス
416.2M
リバウンド率
38.46%
アクセスごとのページ数
6.69
平均受診時間
00:07:31
