pip3 install muq

import torch, librosa
from muq import MuQMuLan

# This will automatically fetch checkpoints from huggingface
device = 'cuda'
mulan = MuQMuLan.from_pretrained("OpenMuQ/MuQ-MuLan-large")
mulan = mulan.to(device).eval()

# Extract music embeddings
wav, sr = librosa.load("path/to/music_audio.wav", sr = 24000)
wavs = torch.tensor(wav).unsqueeze(0).to(device) 
with torch.no_grad():
    audio_embeds = mulan(wavs = wavs) 

# Extract text embeddings (texts can be in English or Chinese)
texts = ["classical genres, hopeful mood, piano.", "一首适合海边风景的小提琴曲，节奏欢快"]
with torch.no_grad():
    text_embeds = mulan(texts = texts)

# Calculate dot product similarity
sim = mulan.calc_similarity(audio_embeds, text_embeds)
print(sim)

import torch, librosa
from muq import MuQ

device = 'cuda'
wav, sr = librosa.load("path/to/music_audio.wav", sr = 24000)
wavs = torch.tensor(wav).unsqueeze(0).to(device) 

# This will automatically fetch the checkpoint from huggingface
muq = MuQ.from_pretrained("OpenMuQ/MuQ-large-msd-iter")
muq = muq.to(device).eval()

with torch.no_grad():
    output = muq(wavs, output_hidden_states=True)

print('Total number of layers: ', len(output.hidden_states))
print('Feature shape: ', output.last_hidden_state.shape)

@article{zhu2025muq,
      title={MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization}, 
      author={Haina Zhu and Yizhi Zhou and Hangting Chen and Jianwei Yu and Ziyang Ma and Rongzhi Gu and Yi Luo and Wei Tan and Xie Chen},
      journal={arXiv preprint arXiv:2501.01108},
      year={2025}
}