README.md

---
license: cc-by-nc-4.0
language:
- ru
base_model:
- microsoft/wavlm-base-plus
pipeline_tag: audio-classification
---
# Music Detection with WavLM

[![arXiv](https://img.shields.io/badge/arXiv-2507.13563-b31b1b.svg)](https://arxiv.org/abs/2507.13563)
[![Conference](https://img.shields.io/badge/INTERSPEECH-2026-1f6feb.svg)](https://arxiv.org/abs/2507.13563)
[![Code](https://img.shields.io/badge/code-lab260ru%2Fbalalaika-181717.svg?logo=github)](https://github.com/lab260ru/balalaika)

> [!IMPORTANT]
> **Official model for our INTERSPEECH 2026 paper**
> *"A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models"* ([arXiv:2507.13563](https://arxiv.org/abs/2507.13563)).
> Part of the **Balalaika** Russian speech data-processing pipeline — code: [https://github.com/lab260ru/balalaika](https://github.com/lab260ru/balalaika).
> If you use this resource, please [cite it](#citation).

Detects if audio contains music.  
**EER: 2.5–3%** | Based on `microsoft/wavlm-base-plus`
*the best threshold value* `0.2442`
---
## Quick Start 
```
git clone https://huggingface.co/MTUCI/MusicDetection
cd MusicDetection
pip install -r requirements.txt
```
##  Usage

```python
from model import WavLMForMusicDetection
from safetensors import safe_open

model = WavLMForMusicDetection(batch_size=32, device='cuda')
with safe_open('music_detection.safetensors', framework="pt") as f:
    model.load_state_dict({k: f.get_tensor(k) for k in f.keys()})

probs = model.predict_proba(['audio1.mp3', 'audio2.wav'])  # → tensor([0.88, 0.11])

## Contact

- Email: kborodin.research@gmail.com
- Telegram: [@korallll_ai](https://t.me/korallll_ai)

## Citation

If you use this resource, please cite our INTERSPEECH 2026 paper:

```bibtex
@inproceedings{borodin2026balalaika,
  title     = {A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative Models},
  author    = {Borodin, Kirill and Vasiliev, Nikita and Kudryavtsev, Vasiliy and Maslov, Maxim and Gorodnichev, Mikhail and Rogov, Oleg and Mkrtchian, Grach},
  booktitle = {Proc. INTERSPEECH 2026},
  year      = {2026},
  note      = {arXiv:2507.13563},
  url       = {https://arxiv.org/abs/2507.13563}
}
```