AIbase
EN
Home
Yourtts Htia 240704
Y

Yourtts Htia 240704

Developed by formospeech
Experimental text-to-speech model trained on five Hakka dialects (Dabu, Hailu, Raoping, Sixian, Zhao'an)
Speech Synthesis
Transformers
 Other#Multi-dialect Hakka speech synthesis#Speaker encoding#Low-resource speech synthesis
Downloads 72
Release Time : 7/4/2024

Model Overview

Multi-dialect Hakka speech synthesis model based on YourTTS architecture, supporting voice generation for 19+ speakers

Model Features

Multi-dialect support
Supports speech synthesis for five Hakka dialects: Dabu, Hailu, Raoping, Sixian, and Zhao'an
Multi-speaker
Training data includes voice samples from over 19 different speakers
Language embedding technology
Utilizes advanced language embedding technology to enhance dialect speech synthesis accuracy
Speaker encoder
Supports voice generation with different speaker styles

Model Capabilities

Text-to-speech
Multi-dialect speech synthesis
Speaker style control

Use Cases

Language preservation
Digital preservation of Hakka dialects
Convert Hakka dialect texts into speech for linguistic cultural heritage preservation
Educational applications
Hakka language learning aid
Generate standard Hakka dialect pronunciations to assist language learners
Smart devices
Dialect voice assistant
Provide dialect voice interaction functionality for Hakka region users
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase