Text-to-Speech
ONNX
Safetensors
English
Chinese
zhu-han commited on
Commit
feb17ad
·
verified ·
1 Parent(s): ae834c6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -8
README.md CHANGED
@@ -13,9 +13,15 @@ tags:
13
 
14
  # ZipVoice⚡: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching</center>
15
 
16
- This model is a checkpoint for **ZipVoice-Dialog**, a non-autoregressive zero-shot spoken dialogue generation model, as presented in [ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching](https://huggingface.co/papers/2507.09318).
 
 
 
 
 
 
 
17
 
18
- You can also find the project/demo page here: [https://zipvoice-dialog.github.io](https://zipvoice-dialog.github.io)
19
 
20
  ## 1. Explanation of each directory
21
 
@@ -29,12 +35,8 @@ You can also find the project/demo page here: [https://zipvoice-dialog.github.io
29
  | zipvoice_dialog_opendialog | ZipVoice-Dialog | OpenDialog | zipvoice/model.pt |
30
  | zipvoice_dialog_stereo | ZipVoice-Dialog-Stereo | in-house dataset | zipvoice_dialog/model.pt |
31
 
32
- ## 2. Github
33
-
34
- See our Github repository [ZipVoice](https://github.com/k2-fsa/ZipVoice) for details
35
-
36
 
37
- ## 3. Discussion & Communication
38
 
39
  You can directly discuss on [Github Issues](https://github.com/k2-fsa/ZipVoice/issues).
40
 
@@ -44,7 +46,7 @@ You can also scan the QR code to join our wechat group or follow our wechat offi
44
  | ------------ | ----------------------- |
45
  |![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_group.jpg) |![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_account.jpg) |
46
 
47
- ## 4. Citation
48
 
49
  ```bibtex
50
  @article{zhu2025zipvoice,
 
13
 
14
  # ZipVoice⚡: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching</center>
15
 
16
+ This model consists of checkpoints for two fast and high-quality non-autoregressive zero-shot text-to-speech models:
17
+
18
+ - **ZipVoice**, for single-speaker speech generation. Details in [paper](https://arxiv.org/abs/2506.13053) and [demo](https://zipvoice.github.io).
19
+
20
+
21
+ - **ZipVoice-Dialog**, for spoken dialogue generation. Details in [paper](https://arxiv.org/abs/2507.09318) and [demo](https://zipvoice-dialog.github.io).
22
+
23
+ See our Github repository [ZipVoice](https://github.com/k2-fsa/ZipVoice) for instructions on using our models.
24
 
 
25
 
26
  ## 1. Explanation of each directory
27
 
 
35
  | zipvoice_dialog_opendialog | ZipVoice-Dialog | OpenDialog | zipvoice/model.pt |
36
  | zipvoice_dialog_stereo | ZipVoice-Dialog-Stereo | in-house dataset | zipvoice_dialog/model.pt |
37
 
 
 
 
 
38
 
39
+ ## 2. Discussion & Communication
40
 
41
  You can directly discuss on [Github Issues](https://github.com/k2-fsa/ZipVoice/issues).
42
 
 
46
  | ------------ | ----------------------- |
47
  |![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_group.jpg) |![wechat](https://k2-fsa.org/zh-CN/assets/pic/wechat_account.jpg) |
48
 
49
+ ## 3. Citation
50
 
51
  ```bibtex
52
  @article{zhu2025zipvoice,