Downloads · 30 days
126
14% of all-time downloads
muscriptor-large-gguf
byzp/muscriptor-large-gguf
muscriptor-large-gguf is a machine learning model from byzp. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Audio-to-MIDI transcription using llama.cpp as the transformer backend.
All-time downloads
905
Public
Repo size
8.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf8.3 GB · 98%
At a glance
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- a39c6f85
Model card
From the Hugging Face model README
MuScriptor
Audio-to-MIDI transcription using llama.cpp as the transformer backend.
8GB VRAM, 8x fast
Prerequisites
- Python with torch, torchaudio
- https://github.com/byzp/llama.cpp built with
llama-serveror download from this repo(linux amd64 cu128) - Model file:
model_fp32_8k.ggufconditioning_weights.safetensors
Extract Conditioning Weights
Only needed once, if starting from the full safetensors:
python extract_conditioning_weights.py
This creates conditioning_weights.safetensors (~11 MB) from the full model weights.
This model can also be downloaded from this repo
CLI Transcription
Terminal 1 — start llama-server:
llama-server -m model_fp32_8k.gguf --port 8081 -ngl 99 --parallel 8
Terminal 2 — run transcription:
python muscriptor_cli.py audio.mp3 -o out.mid
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026