mrfakename / w2v-bert-2.0-music-lyrics-ctc
Audio581M1.3K0Updated Sep 23, 2026
Downloads
1.3K
Likes
0
Last updated
Sep 23, 2026
License
mit
A character-level CTC lyrics model for full music mixes, i.e. vocals with the band, no source separation. It's fine-tuned from w2v-bert-2.0-music, with the encoder unfrozen. It is multilingual: the 921-token vocabulary covers Latin, Cyrillic, Greek, Arabic, Hebrew, Thai, kana/…
Tasks & library
- automatic speech recognition
- transformers
Tags
- transformers
- wav2vec2-bert
- audio
- music
- lyrics
- lyrics-transcription
Technical specifications
Parameters581M
Librarytransformers
LanguagesNot available
Base modelmrfakename/w2v-bert-2.0-music
Licensemit
