Update README.md

README.md

@@ -9,6 +9,7 @@ tags:
 
 # Kanade: A Simple Disentangled Tokenizer for Spoken Language Modeling
 
+[Paper](https://arxiv.org/abs/2602.00594)  
 [Code](https://github.com/frothywater/kanade-tokenizer)  
 [Demo](https://frothywater.github.io/kanade-tokenizer/)  
 
@@ -16,7 +17,7 @@ Kanade is a single-layer disentangled speech tokenizer that extracts compact tok
 
 ## Updates
 
-- **2026-01-09**: Released `kanade-25hz-clean` model trained on [LibriTTS-R](https://arxiv.org/abs/2305.18802) with [HiFT vocoder](https://arxiv.org/abs/2309.09493) for better audio quality. LibriTTS-R is a restored version of LibriTTS removing noise, so the model trained on it can produce cleaner synthesis. Because of that, however, this version can no longer faithfully reflect the recording environment such as background noise and microphone characteristics. Also, the vocoder is changed to the HiFT model used in [CosyVoice 2](https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B) for better quality. The content encoder part remains the same as the previous `kanade-25hz` model. We made tiny code change to support different vocoders during inference (specifically `load_vocoder`). Please refer to the updated usage section below.
+- **2026-01-09**: Released `kanade-25hz-clean` model trained on LibriTTS-R with HiFT vocoder for better audio quality. LibriTTS-R is a restored version of LibriTTS removing noise, so the model trained on it can produce cleaner synthesis. Because of that, however, this version can no longer faithfully reflect the recording environment such as background noise and microphone characteristics. Also, the vocoder is changed to the HiFT model used in [CosyVoice 2](https://huggingface.co/FunAudioLLM/CosyVoice2-0.5B) for better quality. The content encoder part remains the same as the previous `kanade-25hz` model. We made tiny code change to support different vocoders during inference (specifically `load_vocoder`). Please refer to the updated usage section below.
 
 ## Models