仓库议题
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.
议题
此仓库没有开放的已索引议题。
仓库议题
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
此仓库没有开放的已索引议题。
仓库议题
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
此仓库没有开放的已索引议题。