update readme
12
README.md
@@ -1,6 +1,6 @@
|
|||||||
<div align="center">
|
<div align="center">
|
||||||
<div> </div>
|
<div> </div>
|
||||||
<img src="resources/OpenVoiceLogo.png" width="400"/>
|
<img src="resources/OpenVoiceLogo.jpg" width="400"/>
|
||||||
|
|
||||||
[Paper](https://arxiv.org/abs/2312.01479) |
|
[Paper](https://arxiv.org/abs/2312.01479) |
|
||||||
[Website](https://research.myshell.ai/open-voice)
|
[Website](https://research.myshell.ai/open-voice)
|
||||||
@@ -23,7 +23,7 @@ Neither of the language of the generated speech nor the language of the referenc
|
|||||||
|
|
||||||
<div align="center">
|
<div align="center">
|
||||||
<div> </div>
|
<div> </div>
|
||||||
<img src="resources/framework.png" width="800"/>
|
<img src="resources/framework.jpg" width="800"/>
|
||||||
<div> </div>
|
<div> </div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
@@ -39,14 +39,14 @@ OpenVoice has been powering the instant voice cloning capability of [myshell.ai]
|
|||||||
## Live Demo
|
## Live Demo
|
||||||
|
|
||||||
<div align="center">
|
<div align="center">
|
||||||
<a href="https://app.myshell.ai/explore"><img src="resources/myshell.png"></a>
|
<a href="https://app.myshell.ai/explore"><img src="resources/myshell.jpg"></a>
|
||||||
|
|
||||||
<a href="https://www.lepton.ai/playground/openvoice"><img src="resources/lepton.png"></a>
|
<a href="https://www.lepton.ai/playground/openvoice"><img src="resources/lepton.jpg"></a>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
## Disclaimer
|
## Disclaimer
|
||||||
|
|
||||||
**The online version in [myshell.ai](https://app.myshell.ai/explore) does not use this repository**. This is an open-source implementation that approximates the performance of the internal voice clone technology of MyShell.ai.
|
This is an open-source implementation that approximates the performance of the internal voice clone technology of [myshell.ai](https://app.myshell.ai/explore). The online version in myshell.ai has better 1) audio quality, 2) voice cloning similarity, 3) speech naturalness and 4) computational efficiency.
|
||||||
|
|
||||||
## Installation
|
## Installation
|
||||||
Clone this repo, and run
|
Clone this repo, and run
|
||||||
@@ -93,7 +93,7 @@ There are many single or multi-speaker TTS methods that can generate natural spe
|
|||||||
```
|
```
|
||||||
|
|
||||||
## License
|
## License
|
||||||
This repository is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which prohibits commercial usage.
|
This repository is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which prohibits commercial usage. **MyShell reserves the ability to detect whether an audio is generated by OpenVoice**, no matter whether the watermark is added or not.
|
||||||
|
|
||||||
|
|
||||||
## Acknowledgements
|
## Acknowledgements
|
||||||
|
|||||||
@@ -167,7 +167,7 @@
|
|||||||
"id": "8e513094",
|
"id": "8e513094",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"**Tech for good.** For people who will deploy OpenVoice for public usage: We offer you the option to add watermark to avoid potential misuse. Please see the ToneColorConverter class."
|
"**Tech for good.** For people who will deploy OpenVoice for public usage: We offer you the option to add watermark to avoid potential misuse. Please see the ToneColorConverter class. **MyShell reserves the ability to detect whether an audio is generated by OpenVoice**, no matter whether the watermark is added or not."
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
|
|||||||
BIN
resources/OpenVoiceLogo.jpg
Normal file
|
After Width: | Height: | Size: 20 KiB |
|
Before Width: | Height: | Size: 19 KiB |
BIN
resources/framework.jpg
Normal file
|
After Width: | Height: | Size: 147 KiB |
|
Before Width: | Height: | Size: 311 KiB |
BIN
resources/lepton.jpg
Normal file
|
After Width: | Height: | Size: 1.9 KiB |
|
Before Width: | Height: | Size: 1.6 KiB |
BIN
resources/myshell.jpg
Normal file
|
After Width: | Height: | Size: 1.7 KiB |
|
Before Width: | Height: | Size: 1.7 KiB |