倉庫議題
mvanhorn/Fun-ASR
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
議題
此倉庫沒有開放的已索引議題。
倉庫議題
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
此倉庫沒有開放的已索引議題。
倉庫議題
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
此倉庫沒有開放的已索引議題。