Update README.md

README.md

@@ -6,14 +6,14 @@ tags:
 pipeline_tag: audio-to-audio
 ---
 
-# [Xcodec2](https://huggingface.co/HKUSTAudio/xcodec2) (Transformers-compatible version)
+# Xcodec2 (Transformers-compatible version)
 
 
 The X-Codec2 model was proposed in [Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis](https://huggingface.co/papers/2502.04128).
 
 X-Codec2 is a neural audio codec designed to improve speech synthesis and general audio generation for large language model (LLM) pipelines. It extends the original X-Codec by refining how semantic and acoustic information is integrated and tokenized, enabling efficient and high-fidelity audio representation.
 
-Its architecture is based on [X-Codec](./xcodec) with several major differences:
+Its architecture is based on X-Codec with several major differences:
 
 - **Unified Semantic-Acoustic Tokenization**: X-Codec2 fuses outputs from a semantic encoder (e.g., Wav2Vec2-BERT) and an acoustic encoder into a single embedding, capturing both high-level meaning (e.g., text content, emotion) and low-level audio details (e.g., timbre).
 - **Single-Stage Vector Quantization (VQ)**: Unlike the multi-layer residual VQ in most approaches (e.g., [X-Codec](./xcodec), [DAC](./dac), [EnCodec](./encodec)), X-Codec2 uses a single-layer Feature-Space Quantization (FSQ) for stability and compatibility with causal, autoregressive LLMs.
@@ -54,7 +54,7 @@ Here is a quick example of how to encode and decode an audio using this model:
 ```
 
 This model was contributed by [Steven Zheng](https://huggingface.co/Steveeeeeeen) and [Eric Bezzam](https://huggingface.co/bezzam).
-The original code can be found [here](https://github.com/zhenye234/X-Codec-2.0).
+The original code can be found [here](https://github.com/zhenye234/X-Codec-2.0), and original checkpoints [here](https://huggingface.co/HKUSTAudio/xcodec2).