README.md

---
license: cc-by-nc-4.0
tags:
- audio-to-audio
pipeline_tag: audio-to-audio
---

[![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/abs/2502.04128)

**Update (2026-06-25):** A Transformers-native version of Xcodec2 has been released [here](https://huggingface.co/HKUSTAudio/xcodec2-hf)!

**Update (2025-02-13):** Add [Llasa finetune instruction](https://github.com/zhenye234/LLaSA_training/tree/main/finetune).

**Update (2025-02-07):** Our paper has been released!


## Paper
 
LLaSA: Scaling Train Time and Inference Time Compute for LLaMA based Speech Synthesis  

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model (AAAI 2025, xcodec 1.0)


# Getting Started with XCodec2 on Hugging Face
XCodec2 is a speech tokenizer that offers the following key features:

1. **Single Vector Quantization**
2. **50 Tokens per Second**
3. **Multilingual Speech Semantic Support and High-Quality Speech Reconstruction**


To use `xcodec2`, ensure you have it installed. You can install it using the following command:

```bash
conda create -n xcodec2 python=3.9
conda activate xcodec2
pip install xcodec2  (Use `xcodec2==0.1.5` for codec inference and llasa fine-tuning. I’ve removed unnecessary dependencies, and it works fine in my testing. However,  I’m not sure if other problems may arise. If you prefer more stability, I recommend using `xcodec2==0.1.3` which accurately aligns during my codec training.)
 
```
Then,
```python
import torch
import soundfile as sf
from transformers import AutoConfig

 
from xcodec2.modeling_xcodec2 import XCodec2Model
 
model_path = "HKUSTAudio/xcodec2"  
 
model = XCodec2Model.from_pretrained(model_path)
model.eval().cuda()   

 
wav, sr = sf.read("test.wav")   
wav_tensor = torch.from_numpy(wav).float().unsqueeze(0)  # Shape: (1, T)

 
with torch.no_grad():
   # Only 16khz speech
   # Only supports single input. For batch inference, please refer to the link below.
    vq_code = model.encode_code(input_waveform=wav_tensor)
    print("Code:", vq_code )  

    recon_wav = model.decode_code(vq_code).cpu()       # Shape: (1, 1, T')

 
sf.write("reconstructed.wav", recon_wav[0, 0, :].numpy(), sr)
print("Done! Check reconstructed.wav")
```

# If you want to train your own xcodec2, batch inference, or large-scale code extraction, the code is released [here](https://github.com/zhenye234/X-Codec-2.0).