Update README.md
Browse files
README.md
CHANGED
|
@@ -25,9 +25,6 @@
|
|
| 25 |
## Introduction
|
| 26 |
We are open-sourcing Step-Audio-EditX, a powerful **3B-parameter** LLM-based **Reinforcement Learning** audio model specialized in expressive and iterative audio editing. It excels at editing emotion, speaking style, and paralinguistics, and also features robust zero-shot text-to-speech (TTS) capabilities.
|
| 27 |
|
| 28 |
-

|
| 29 |
-
WeChat Developer Group
|
| 30 |
-
|
| 31 |
## 📑 Open-source Plan
|
| 32 |
- [x] Inference Code
|
| 33 |
- [x] Online demo (Gradio)
|
|
@@ -48,7 +45,30 @@ WeChat Developer Group
|
|
| 48 |
- [ ] Other Languages
|
| 49 |
- [x] Japanese, Korean
|
| 50 |
- [ ] Arabic, French, Russian, Spanish, etc.
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
## Features
|
| 53 |
- **Zero-Shot TTS**
|
| 54 |
- Excellent zero-shot TTS cloning for Mandarin, English, Sichuanese, and Cantonese.
|
|
|
|
| 25 |
## Introduction
|
| 26 |
We are open-sourcing Step-Audio-EditX, a powerful **3B-parameter** LLM-based **Reinforcement Learning** audio model specialized in expressive and iterative audio editing. It excels at editing emotion, speaking style, and paralinguistics, and also features robust zero-shot text-to-speech (TTS) capabilities.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
| 28 |
## 📑 Open-source Plan
|
| 29 |
- [x] Inference Code
|
| 30 |
- [x] Online demo (Gradio)
|
|
|
|
| 45 |
- [ ] Other Languages
|
| 46 |
- [x] Japanese, Korean
|
| 47 |
- [ ] Arabic, French, Russian, Spanish, etc.
|
| 48 |
+
|
| 49 |
+
## Online demonstration
|
| 50 |
+
|
| 51 |
+
### StepFun Audio Studio
|
| 52 |
+
|
| 53 |
+
- Both Step-Audio-EditX are available in our [StepFun Audio Studio](https://www.stepfun.com/studio/audio).
|
| 54 |
+
- You will need an API key from the [StepFun Open Platform](https://platform.stepfun.com/).
|
| 55 |
+
|
| 56 |
+
### StepFun AI Assistant
|
| 57 |
+
|
| 58 |
+
- Step-Audio 2 is also available in our StepFun AI Assistant mobile App with both web and audio search tools enabled.
|
| 59 |
+
- Please scan the following QR code to download it from your app store then tap the phone icon in the top-right corner.
|
| 60 |
+
|
| 61 |
+
<div align="center">
|
| 62 |
+
<img src="./assets/qrcode.jpg" width="200" alt="QR code">
|
| 63 |
+
</div>
|
| 64 |
+
|
| 65 |
+
## WeChat group
|
| 66 |
+
|
| 67 |
+
You can scan the following QR code to join our WeChat group for communication and discussion.
|
| 68 |
+
<div align="center">
|
| 69 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/66518fd07d8cb2629a514c18/DRdnp1SN-yxhlNOfy26mE.jpeg" width="200" alt="QR code">
|
| 70 |
+
</div>
|
| 71 |
+
|
| 72 |
## Features
|
| 73 |
- **Zero-Shot TTS**
|
| 74 |
- Excellent zero-shot TTS cloning for Mandarin, English, Sichuanese, and Cantonese.
|