Update README.md

README.md

@@ -11,16 +11,16 @@ library_name: transformers
 
 # TTS Evaluation Models
 
-This repository contains models for the objective evaluation of text-to-speech (TTS) models, as presented in the papers [ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching](https://huggingface.co/papers/2506.13053) and [ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching](https://huggingface.co/papers/2507.09318).
+This repository contains models for the objective evaluation of text-to-speech (TTS) models, as presented in the papers [ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching](https://huggingface.co/papers/2506.13053), [ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching](https://huggingface.co/papers/2507.09318), [OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models](https://huggingface.co/papers/2604.00688).
+
+- **Code:** [k2-fsa/ZipVoice](https://github.com/k2-fsa/ZipVoice) and [k2-fsa/OmniVoice](https://github.com/k2-fsa/OmniVoice)
 
-- **Code:** [k2-fsa/ZipVoice](https://github.com/k2-fsa/ZipVoice)
-- **Project Page:** [ZipVoice-Dialog Demos](https://zipvoice-dialog.github.io)
 
 ## Evaluation Metrics
 
 This repository specifically supports the following evaluation metrics:
 
-- **WER**: Includes [Hubert-based ASR model](https://huggingface.co/facebook/hubert-large-ls960-ft) for LibriSpeech-PC testset, [Paraformer-based ASR model](https://huggingface.co/funasr/paraformer-zh) for Chinese datasets, [Whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) model for general English test sets, [WhisperD](https://huggingface.co/jordand/whisper-d-v1a) model for English dialogue speech.
+- **WER**: Includes [Hubert-based ASR model](https://huggingface.co/facebook/hubert-large-ls960-ft) for LibriSpeech-PC testset, [Paraformer-based ASR model](https://huggingface.co/funasr/paraformer-zh) for Chinese datasets, [Whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) model for general English and other languages test sets, [WhisperD](https://huggingface.co/jordand/whisper-d-v1a) model for English dialogue speech.
 
 - **cpWER**: [WhisperD](https://huggingface.co/jordand/whisper-d-v1a) model is used to compute concatenated minimum permutation word error rate ([cpWER](https://arxiv.org/abs/2507.09318)) for English dialogue speech.
 
@@ -30,7 +30,7 @@ This repository specifically supports the following evaluation metrics:
 
 - **UTMOS**: The mos prediction model [UTMOS](https://github.com/sarulab-speech/UTMOS22) is used.
 
-For more details, please refer to the [official repository](https://github.com/k2-fsa/ZipVoice).
+For more details, please refer to repositories [ZipVoice](https://github.com/k2-fsa/ZipVoice) and [OmniVoice](https://github.com/k2-fsa/OmniVoice).
 
 ## Citation
 
@@ -48,4 +48,12 @@ For more details, please refer to the [official repository](https://github.com/k
       journal={arXiv preprint arXiv:2507.09318},
       year={2025}
 }
+
+@article{zhu2026omnivoice,
+      title={OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models},
+      author={Zhu, Han and Ye, Lingxuan and Kang, Wei and Yao, Zengwei and Guo, Liyong and Kuang, Fangjun and Han, Zhifeng and Zhuang, Weiji and Lin, Long and Povey, Daniel},
+      journal={arXiv preprint arXiv:2604.00688},
+      year={2026}
+}
+
 ```