Instructions to use VincentGOURBIN/sheetsage2-mlx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use VincentGOURBIN/sheetsage2-mlx-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download VincentGOURBIN/sheetsage2-mlx-fp16 --local-dir sheetsage2-mlx-fp16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
SheetSage2 for MLX Swift โ merged fp16
Music recording โ editable ABC score, on Apple silicon (Mac, iPhone), with
yue2-mlx-swift (SheetSage2Core, yue2 transcribe).
The score feeds a YuE2 cover with cot: melody.
Source and changes
A derivative of SheetSage2 (m-a-p/SheetSage2, revision
398b22834dac) and of its encoder parent MERT2 (m-a-p/MERT-v2-FullSong,
revision d8ba1c745e73, the one SheetSage2 pins), both by m-a-p, CC BY-NC 4.0. Changes made here:
- the LoRA adapters merged into MERT2's attention projections (upstream
merge_lora, float32); - weights cast to float16, except the mel front-end buffers, the ConvNeXt front and the layer-mix logits, kept in float32 as the Swift port computes them;
- packaged as one safetensors file (PyTorch key layout,
weights_format: merged), SHA-256 inmodel.safetensors.sha256. No retraining, no other modification. The weights are not endorsed by m-a-p.
Use
yue2 download --model sheetsage2-fp16 # 1.4 GB, SHA-256 verified
yue2 transcribe --audio song.m4a --profile 16bit-lean --out run/score
Fidelity: with the Swift port, this pack gives the same tokens and ABC as the upstream release merged
at load (16bit-* profiles); in float32 the port is byte-identical to the upstream PyTorch code.
Measurements and profiles: the repository's docs/References.md.
License
CC BY-NC 4.0 (see LICENSE, copied from the upstream release): non-commercial use only, with
attribution to MERT2 and SheetSage2 (m-a-p) and their repositories above.
- Downloads last month
- 49
Quantized
Model tree for VincentGOURBIN/sheetsage2-mlx-fp16
Base model
m-a-p/MERT-v2-FullSong