---
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.