Spaces:
Running
Running
title: Csm 1b Gradio | |
emoji: 🔥 | |
colorFrom: blue | |
colorTo: green | |
sdk: gradio | |
sdk_version: 5.21.0 | |
app_file: app.py | |
pinned: false | |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |
# CSM-1B Gradio Demo | |
Demo application for the CSM-1B (Conversational Speech Model) using Gradio to create a user-friendly interface. | |
## Features | |
- Convert text to natural-sounding speech | |
- Support for multiple speaker voices (Speaker IDs) | |
- Generate speech with conversation context | |
- Customize parameters like temperature and audio length | |
## Usage | |
1. Enter the text you want to convert to speech | |
2. Choose a speaker ID (from 0-10) | |
3. Customize advanced parameters (optional) | |
4. Add conversation context if needed | |
5. Click "Generate Audio" to hear the result | |
## Deployment on Hugging Face Spaces | |
This application is designed to run on Hugging Face Spaces. To deploy: | |
1. Create a new Space | |
2. Upload the source code to the Space | |
3. Select Gradio as the framework | |
4. Wait for the application to build and start | |
## Resources | |
Sesame AI's CSM-1B model: [sesame/csm-1b](https://huggingface.co/sesame/csm-1b) | |