Hugging Face's logo

FEAfeatherTHER
/
CPR

audio
music-generation
midi-to-audio
audio-super-resolution
Model card Files
xet
 Community
1
CPR / README.md
nielsr's picture
nielsr HF Staff
Add pipeline tag, link to paper and code
4989517 verified
preview code
|
Raw History Blame
2.61 kB
metadata 
tags:
  - audio
  - music-generation
  - midi-to-audio
  - audio-super-resolution
pipeline_tag: audio-to-audio

CPR: COMBINING GLOBAL COMPOSING, LOCAL PERFORMING AND FULL-SEQUENCE REFINING IN PIANO RENDERING WITH CONTINUOUS AUTOREGRESSIVE MODELLING

This model is presented in the paper CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling.

Code is available at github.com/FEAfeatherTHER/CPR_official.

  1. Composer–Performer (CP) takes prompt audio, prompt MIDI, and target MIDI, and renders 24 kHz mono audio. The Composer is an autoregressive Qwen3 Transformer; the Performer renders local Mel spectrograms with flow matching. A Vocos vocoder converts the generated Mel spectrograms to audio.
  2. Refiner (R) takes a 24 kHz audio file and writes 48 kHz mono audio using the LavaSR-based bandwidth-extension model and low-frequency fusion.

Installation

Create a Conda environment with Python 3.10:

conda create -n cpr python=3.10
conda activate cpr
pip install -r requirements.txt

On the first CP run, CLAP automatically downloads and caches its RoBERTa initialization resources.

Checkpoints

Download the inference assets from Huggingface into checkpoints/.

hf download bruceL33/CPR \
  composer_performer.safetensors \
  composer_performer_config.json \
  vocos.safetensors \
  refiner.bin \
  --local-dir checkpoints
Component File under checkpoints/
Composer–Performer composer_performer.safetensors
Model architecture and Qwen configuration composer_performer_config.json
24 kHz Vocos vocoder vocos.safetensors
Refiner refiner.bin

Download CLAP

CLAP is required for Composer–Performer inference. Download the official music checkpoint music_audioset_epoch_15_esc_90.14.pt and save it as checkpoints/clap.pt:

curl --fail --location \
  --output checkpoints/clap.pt \
  https://huggingface.co/lukewys/laion_clap/resolve/main/music_audioset_epoch_15_esc_90.14.pt

Inference

1. Composer–Performer → 24 kHz 

bash scripts/infer_cp.sh

2. Refiner → 48 kHz

use any existing 24 kHz WAV or the output of Composer-Performer:

python infer_refiner.py --input /path/to/audio_24k.wav --output outputs/refined.wav