Tunisian TTS
XTTS V2 text-to-speech model fine-tuned on a custom Tunisian dataset
Downloads 48
Release Time : 2/25/2025
Model Overview
This model is a fine-tuned version of coqui ai/xtts v2 on a custom Tunisian dataset (2 hours 30 minutes), specifically designed for Tunisian dialect text-to-speech tasks.
Model Features
Tunisian dialect optimization
Specially fine-tuned for Tunisian dialect, delivering more natural speech synthesis
Efficient training
Requires only 2 hours 30 minutes of Tunisian data for fine-tuning
Lightweight
Batch size of only 2, suitable for resource-constrained environments
Model Capabilities
Tunisian text-to-speech
Arabic dialect speech synthesis
Use Cases
Voice applications
Tunisian voice assistant
Developing localized voice assistants for the Tunisian region
Provides more natural Tunisian dialect voice output
Educational applications
Speech synthesis for Tunisian language learning apps
Helps learners familiarize with Tunisian dialect pronunciation
Featured Recommended AI Models