Update README.md

README.md

@@ -19,7 +19,7 @@ language:
 
 # 🗣️ XCodec2 Trained on 100K Hours of Multilingual Data
 
-This [model](https://huggingface.co/HKUSTAudio/xcodec2) is trained on a 100K-hour multilingual dataset across 7 languages. It is optimized for speech representation learning, compression, and high-fidelity reconstruction — particularly useful for TTS and bandwidth-efficient speech synthesis.
+This is a retrained version of the XCodec2 neural audio codec by HKUSTAudio, using 100,000 hours of multilingual speech across seven languages. The model enables efficient speech compression and reconstruction for low-bandwidth, high-quality audio applications. Its discrete token outputs are well-suited for LLM-based TTS, AudioLM, multimodal models, and speech-to-speech systems, making it a versatile solution for multilingual and real-world speech processing tasks.
 
 ---