Ray0323 commited on
Commit
64af293
·
verified ·
1 Parent(s): e308122

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -13
README.md CHANGED
@@ -11,11 +11,13 @@ license: cc-by-nc-4.0
11
  <p>
12
  </p>
13
  </p>
14
- <a href="https" style="color:red">Paper </a> |
15
- <a href="https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0" style="color:#FFD700">Hugging Face Model</a>
16
  <a href="https://github.com/IDEA-Emdoor-Lab/DistilCodec" style="color:gray">Code</a>
17
  <p>
18
  <img src="./idea_logo.png" alt="Institution 1" style="width: 200px; height: 60px;">
 
 
19
  <img src="./yidao_logo.png" alt="Institution 2" style="width: 200px; height: 60px;">
20
  <img src="./yijiayiban.png" alt="Institution 3" style="width: 200px; height: 60px;">
21
  </p>
@@ -23,9 +25,9 @@ license: cc-by-nc-4.0
23
 
24
 
25
  # 🔥 News
26
- - *2025.05.27*: We release DistilCodec-v1.0 checkpoint on [huggingface](https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0).
27
- - *2025.05.26*: We release the code of DistilCodec-v1.0, including training and inference.
28
- - *2025.05.24*: We release UniTTS and DistilCodec on [arxiv](https://arxiv.org/abs/2408.16532).
29
 
30
  ## Introduction of DistilCodec
31
  The Joint Laboratory of International Digital Economy Academy (IDEA) and Emdoor, in collaboration with Emdoor Information Technology Co., Ltd., and Shenzhen Yijiayiban Information Technology Co., Ltd, has launched DistilCodec - A Single-Codebook Neural Audio Codec (NAC) with 32768 codes trained on uniersal audio.The foundational network architecture of DistilCodec adopts an Encoder-VQ-Decoder framework
@@ -121,18 +123,38 @@ codec.save_wav(
121
  ## Available DistilCodec models
122
  |Model Version| Huggingface | Corpus | Token/s | Domain |
123
  |-----------------------|---------|---------------|---------------|-----------------------------------|
124
- | DistilCodec-v1.0 | [HF](https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0) | Universal Audio | 93 | Audiobook、Speech、Audio Effects |
125
 
126
 
127
  ## Citation
128
 
129
- If you find this code useful in your research, please cite our work:
130
 
131
  ```
132
- @article{wang2025unitts,
133
- title={UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information},
134
- author={Rui Wang,Qianguo Sun,Tianrong Chen,Zhiyun Zeng,Junlong Wu,Jiaxing Zhang},
135
- journal={arXiv preprint arXiv:2408.16532},
136
- year={2025}
 
 
 
137
  }
138
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  <p>
12
  </p>
13
  </p>
14
+ <a href="https://arxiv.org/abs/2505.17426" style="color:red">Paper </a> |
15
+ <a href="https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0" style="color:#FFD700">HuggingFace Model</a> |
16
  <a href="https://github.com/IDEA-Emdoor-Lab/DistilCodec" style="color:gray">Code</a>
17
  <p>
18
  <img src="./idea_logo.png" alt="Institution 1" style="width: 200px; height: 60px;">
19
+ </p>
20
+ <p>
21
  <img src="./yidao_logo.png" alt="Institution 2" style="width: 200px; height: 60px;">
22
  <img src="./yijiayiban.png" alt="Institution 3" style="width: 200px; height: 60px;">
23
  </p>
 
25
 
26
 
27
  # 🔥 News
28
+ - *2025.05.26*: We release DistilCodec-v1.0 checkpoint on [huggingface](https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0).
29
+ - *2025.05.26*: The paper is available on [arxiv](https://arxiv.org/abs/2505.17426).
30
+ - *2025.05.23*: We submit paper to arxiv.
31
 
32
  ## Introduction of DistilCodec
33
  The Joint Laboratory of International Digital Economy Academy (IDEA) and Emdoor, in collaboration with Emdoor Information Technology Co., Ltd., and Shenzhen Yijiayiban Information Technology Co., Ltd, has launched DistilCodec - A Single-Codebook Neural Audio Codec (NAC) with 32768 codes trained on uniersal audio.The foundational network architecture of DistilCodec adopts an Encoder-VQ-Decoder framework
 
123
  ## Available DistilCodec models
124
  |Model Version| Huggingface | Corpus | Token/s | Domain |
125
  |-----------------------|---------|---------------|---------------|-----------------------------------|
126
+ | DistilCodec-v1.0 | [HuggingFace](https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0) | Universal Audio | 93 | Universal Audio |
127
 
128
 
129
  ## Citation
130
 
131
+ If you find our work useful in your research, please cite our work:
132
 
133
  ```
134
+ @misc{wang2025unittsendtoendttsdecoupling,
135
+ title={UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information},
136
+ author={Rui Wang and Qianguo Sun and Tianrong Chen and Zhiyun Zeng and Junlong Wu and Jiaxing Zhang},
137
+ year={2025},
138
+ eprint={2505.17426},
139
+ archivePrefix={arXiv},
140
+ primaryClass={cs.SD},
141
+ url={https://arxiv.org/abs/2505.17426},
142
  }
143
+ ```
144
+
145
+
146
+ ## Disclaimer
147
+
148
+ DistilCodec provides the capability of universal audio discretion only for academic research purposes. We encourage the community to uphold safety and ethical principles in AI research and applications.
149
+
150
+ Important Notes:
151
+
152
+ - Compliance with the model's open-source license is mandatory.
153
+
154
+ - Unauthorized voice replication applications are strictly prohibited.
155
+
156
+ - Developers bear no responsibility for any misuse of this model.
157
+
158
+
159
+ ## License
160
+ <a href="https://arxiv.org/abs/2505.17426">UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information</a> © 2025 by <a href="https://creativecommons.org">Rui Wang, Qianguo Sun, Tianrong Chen, Zhiyun Zeng, Junlong Wu, Jiaxing Zhang</a> is licensed under <a href="https://creativecommons.org/licenses/by-nc-nd/4.0/">CC BY-NC-ND 4.0</a><img src="https://mirrors.creativecommons.org/presskit/icons/cc.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;"><img src="https://mirrors.creativecommons.org/presskit/icons/by.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;"><img src="https://mirrors.creativecommons.org/presskit/icons/nc.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;"><img src="https://mirrors.creativecommons.org/presskit/icons/nd.svg" style="max-width: 1em;max-height:1em;margin-left: .2em;">