Improve model card for XY-Tokenizer

This PR significantly improves the model card for the XY-Tokenizer model by:

* **Adding comprehensive details**: The full content from the project's GitHub README has been integrated, including an overview, key highlights, installation instructions, and usage examples.
* **Enhancing discoverability**: The `pipeline_tag: audio-to-audio` has been added to the metadata, ensuring the model can be easily found under relevant tasks on the Hugging Face Hub (https://huggingface.co/models?pipeline_tag=audio-to-audio).
* **Specifying the library**: The `library_name: pytorch` tag has been added, indicating the primary framework used for the model.
* **Providing essential links**: Direct links to the paper ([XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs](https://huggingface.co/papers/2506.23325)), the official GitHub repository (https://github.com/gyt1145028706/XY-Tokenizer), and the Hugging Face model page are now prominently featured.
* **Cleaning up content**: Broken or unconfirmed links (e.g., for blog/demos) have been removed or updated, and the image path has been corrected for rendering on the Hub.

Please review and merge this PR to provide a more complete and helpful resource for the community.

README.md

@@ -1,3 +1,101 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: audio-to-audio
+library_name: pytorch
+---
+
+# XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs
+
+This repository contains the model weights for **XY-Tokenizer**, a novel speech codec introduced in the paper [XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs](https://huggingface.co/papers/2506.23325).
+
+[[Paper]](https://huggingface.co/papers/2506.23325) | [[GitHub]](https://github.com/gyt1145028706/XY-Tokenizer) | [[Hugging Face Model Page]](https://huggingface.co/fdugyt/XY_Tokenizer)
+
+## Overview 🔍
+
+**XY-Tokenizer** is a novel speech codec designed to bridge the gap between speech signals and large language models by simultaneously **modeling both semantic and acoustic information**. It operates at a bitrate of **1 kbps** (1000 bps), using **8-layer Residual Vector Quantization (RVQ8)** at a **12.5 Hz** frame rate.
+
+At this ultra-low bitrate, **XY-Tokenizer** achieves performance comparable to state-of-the-art speech codecs that focus on only one aspect—either semantic or acoustic—while **XY-Tokenizer** performs strongly on both. You can also find the model on [Hugging Face](https://huggingface.co/fdugyt/XY_Tokenizer).
+
+## Highlights ✨
+
+- **Low frame rate, low bitrate with high fidelity and text alignment**: Achieves strong semantic alignment and acoustic quality at 12.5Hz and 1kbps.
+
+- **Multilingual training on the full Emilia dataset**: Trained on a large-scale multilingual dataset, supporting robust performance across diverse languages.
+
+- **Designed for Speech LLMs**: Can be used for zero-shot TTS, dialogue TTS (e.g., [MOSS-TTSD](https://github.com/OpenMOSS/MOSS-TTSD)), and speech large language models.
+
+<div align="center">
+    <p>
+    <img src="https://huggingface.co/fdugyt/XY_Tokenizer/resolve/main/assets/XY-Tokenizer-Architecture.png" alt="XY-Tokenizer" width="1000">
+    </p>
+</div>
+
+## News 📢
+
+- **[2025-06-28]** We released the code and checkpoints of XY-Tokenizer. Check out our [paper](https://huggingface.co/papers/2506.23325)!
+
+## Installation 🛠️
+
+To use XY-Tokenizer, you need to install the required dependencies. You can use either pip or conda to set up your environment.
+
+### Using conda
+
+```bash
+# Clone repository
+git clone [email protected]:gyt1145028706/XY-Tokenizer.git && cd XY-Tokenizer
+
+# Create and activate conda environment
+conda create -n xy_tokenizer python=3.10 -y && conda activate xy_tokenizer
+
+# Install dependencies
+pip install -r requirements.txt
+```
+
+## Available Models 🗂️
+
+| Model Name | Hugging Face | Training Data |
+|:----------:|:-------------:|:---------------:|
+| XY-Tokenizer | [🤗](https://huggingface.co/fdugyt/XY_Tokenizer) | Emilia |
+| XY-Tokenizer-TTSD-V0 (used in [MOSS-TTSD](https://github.com/OpenMOSS/MOSS-TTSD)) | [🤗](https://huggingface.co/fnlp/XY_Tokenizer_TTSD_V0/) | Emilia + Internal Data (containing general audio) |
+
+## Usage 🚀
+
+### Download XY Tokenizer
+
+You need to download the XY Tokenizer model weights. You can find the weights in the [XY_Tokenizer Hugging Face repository](https://huggingface.co/fdugyt/XY_Tokenizer).
+
+```bash
+mkdir -p ./weights && huggingface-cli download fdugyt/XY_Tokenizer xy_tokenizer.ckpt --local-dir ./weights/
+```
+
+### Local Inference
+
+First, set the Python path to include this repository:
+```bash
+export PYTHONPATH=$PYTHONPATH:./
+```
+
+Then you can tokenize audio to speech tokens and generate reconstructed audio from these tokens by running:
+```python
+python inference.py
+```
+
+The reconstructed audio files will be available in the `output_wavs/` directory.
+
+## License 📜
+
+XY-Tokenizer is released under the Apache 2.0 license.
+
+## Citation 📚
+
+```bibtex
+@misc{gong2025xytokenizermitigatingsemanticacousticconflict,
+      title={XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs},
+      author={Yitian Gong and Luozhijie Jin and Ruifan Deng and Dong Zhang and Xin Zhang and Qinyuan Cheng and Zhaoye Fei and Shimin Li and Xipeng Qiu},
+      year={2025},
+      eprint={2506.23325},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2506.23325},
+}
+```