ModelListadosExterno

MuQ Eval A1

Multi-head neural evaluator for music generation quality, built on frozen MuQ representations with learned attention pooling and per-dimension MLP prediction heads.

Fontehuggingface.co/zhudi2825/MuQ-Eval-A1/tree/b082e238827df51d99ac66bdd1b6f0d2406bc90e

TipoOtherVersãoRevision b082e23Bnota

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 1,24–1,25 GB
Versão: vRevision b082e23
Atualizado: 22 de set. de 2026
Downloads: 913
Fonte: Hugging Face

Descrição da fonte

MusicQualityModel — A1_frozen_mlp

Multi-head neural evaluator for music generation quality, built on frozen MuQ representations with learned attention pooling and per-dimension MLP prediction heads.

Model Details

Encoder: OpenMuQ/MuQ-large-msd-iter (tuning mode: frozen)
Pooling: Attention-weighted mean pooling
Heads: MI, TA
Loss: mse
Input: Audio waveform at 24000 Hz, max 10.0s

Performance

Evaluated with 5-fold cross-validation on MusicEval (2,748 clips, 31 TTM systems).

Usage

import torch
import torchaudio
from omegaconf import OmegaConf
from huggingface_hub import hf_hub_download

# Download files
config_path = hf_hub_download("zhudi2825/MuQ-Eval-A1", "config.yaml")
model_path = hf_hub_download("zhudi2825/MuQ-Eval-A1", "best_model.pt")

# Load config and build model
cfg = OmegaConf.load(config_path)
from src.model import MusicQualityModel
model = MusicQualityModel(cfg)

ckpt = torch.load(model_path, map_location="cpu", weights_only=False)
model.load_state_dict(ckpt["model_state"])
model.eval()

# Run inference
waveform, sr = torchaudio.load("audio.wav")
if sr != 24000:
    waveform = torchaudio.transforms.Resample(sr, 24000)(waveform)
waveform = waveform.mean(0)  # mono
waveform = waveform[:240000].unsqueeze(0)  # [1, samples]

with torch.no_grad():
    preds = model(waveform)
    scores = model._last_expected_scores
    for name, score in scores.items():
        print(f"{name}: {score.item():.2f}")

Training

Dataset: MusicEval (BAAI/MusicEval) — 5-fold stratified CV by TTM model
Epochs: 30
Batch size: 16
Optimizer: AdamW (lr=0.001, wd=0.01)
Scheduler: cosine with 500 warmup steps
Precision: bf16

Citation

If you use this model, please cite:

@article{zhu2026muqeval,
  title={Frozen Music Representations Suffice for Per-Sample Quality Prediction of Generated Music},
  author={Zhu, Di and Li, Zixuan},
  journal={arXiv preprint arXiv:2603.22677},
  year={2026}
}

Fontes

1 fonte

Hugging FacePrimárioVersão b082e238827df51d99ac66bdd1b6f0d2406bc90e

huggingface.co/zhudi2825/MuQ-Eval-A1/tree/b082e238827df51d99ac66bdd1b6f0d2406bc90e

Verificado 6 de set.

Artefatos de modelo

2 artefatos

best_model.pt

pt · 1,25 GB · SHA-256 681048d045e9…eaac · Hugging Face

Baixar

model_state_dict.pt

pt · 1,24 GB · SHA-256 4163ec9ba81b…1455 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme6 de set.huggingface.co/zhudi2825/MuQ-Eval-A1

--- language: en library_name: pytorch license: mit pipeline_tag: audio-classification tags: - audio - music - quality-assessment - MOS-prediction - music-generation --- # MusicQualityModel — A1_frozen_mlp Multi-head neural evaluator for music generation quality, built on frozen [MuQ](https://huggingface.co/OpenMuQ/MuQ-large-msd-iter) representations with learned attention pooling and per-dimension MLP prediction heads. ## Model Details - **Encoder:** `OpenMuQ/MuQ-large-msd-iter` (tuning mode: `frozen`) - **Pooling:** Attention-weighted mean pooling - **Heads:** MI, TA - **Loss:** `mse` - **Input:** Audio waveform at 24000 Hz, max 10.0s ## Performance Evaluated with 5-fold cross-validation on MusicEval (2,748 clips, 31 TTM systems). ## Usage ```python import torch import torchaudio from omegaconf import OmegaConf from huggingface_hub import hf_hub_download # Download files config_path = hf_hub_download("zhudi2825/MuQ-Eval-A1", "config.yaml") model_path = hf_hub_download("zhudi2825/MuQ-Eval-A1", "best_model.pt") # Load config and build model cfg = OmegaConf.load(config_path) from src.model import MusicQualityModel model = MusicQualityModel(cfg) ckpt = torch.load(model_path, map_location="cpu", weights_only=False) model.load_state_dict(ckpt["model_state"]) model.eval() # Run inference waveform, sr = torchaudio.load("audio.wav") if sr != 24000: waveform = torchaudio.transforms.Resample(sr, 24000)(waveform) waveform = waveform.mean(0) # mono waveform = waveform[:240000].unsqueeze(0) # [1, samples] with torch.no_grad(): preds = model(waveform) scores = model._last_expected_scores for name, score in scores.items(): print(f"{name}: {score.item():.2f}") ``` ## Training - **Dataset:** MusicEval (BAAI/MusicEval) — 5-fold stratified CV by TTM model - **Epochs:** 30 - **Batch size:** 16 - **Optimizer:** AdamW (lr=0.001, wd=0.01) - **Scheduler:** cosine with 500 warmup steps - **Precision:** bf16 ## Citation If you use this model, please cite: ```bibtex @article{zhu2026muqeval, title={Frozen Music Representations Suffice for Per-Sample Quality Prediction of Generated Music}, author={Zhu, Di and Li, Zixuan}, journal={arXiv preprint arXiv:2603.22677}, year={2026} } ```

Note6 de set.huggingface.co/zhudi2825/MuQ-Eval-A1

Source context: 913 downloads · 0 likes · Pipeline audio-classification · Library pytorch · Repo zhudi2825/MuQ-Eval-A1