| license: other | |
| license_name: cc-by-nc-sa-4.0 | |
| license_link: https://creativecommons.org/licenses/by-nc-sa/4.0/ | |
| tags: | |
| - audio-to-score-transcription | |
| - music-information-retrieval | |
| - lead-sheet | |
| - lyrics | |
| library_name: pytorch | |
| # SheetSage-A2LS model checkpoints | |
| Model checkpoints for **Audio-to-Lead-Sheet Transcription (A2LS)**, the retrained | |
| models described in our paper (under review). Each checkpoint greedily decodes a | |
| Humdrum `**kern` lead sheet (melody `**kern`, chords `**cdata`, lyrics `**text`) | |
| from pre-computed [MuQ](https://github.com/tencent-ailab/MuQ) features. | |
| | file | lyrics tokeniser (`--lyrics_tokeniser`) | | |
| |---|---| | |
| | `cummins_retrained.ckpt` | `none` | | |
| | `word_tok.ckpt` | `word` | | |
| | `char_tok.ckpt` | `character` | | |
| | `bpe_tok.ckpt` | `bpe` (GPT-2) | | |
| Inference and evaluation code: [GitHub repository](https://github.com/Multimodal-Music-Research-Lab/Audio-to-Lead-Sheet-Transcription). | |
| Weights are released under CC-BY-NC-SA 4.0. | |