A newer version of the Gradio SDK is available: 6.13.0
metadata
title: SwaGPT
emoji: π
colorFrom: yellow
colorTo: pink
sdk: gradio
sdk_version: 6.3.0
app_file: app.py
pinned: false
license: apache-2.0
title: SwaGPT - Kiswahili Text-to-Speech emoji: ποΈ colorFrom: blue colorTo: indigo sdk: gradio sdk_version: 4.0.0 app_file: app.py pinned: false
SwaGPT: Kiswahili Text-to-Speech
This is a Gradio application for SwaGPT, a Kiswahili Text-to-Speech (TTS) system inspired by the work of Saheed Azeez on YarnGPT.
Model Details
The system utilizes the Facebook MMS (Massively Multilingual Speech) model, specifically the facebook/mms-tts-swh checkpoint, which is optimized for high-quality Kiswahili speech synthesis.
Usage
Simply enter your Kiswahili text in the box and click "Tengeneza Sauti" to generate the audio.
Code
The core logic is contained in app.py, which loads the pre-trained model and tokenizer from the Hugging Face Hub.
License
This project is licensed under the Apache 2.0 License.
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference