Diana Hungarian Tts Vits
A VITS-based speech synthesis model trained on KTH's Hungarian single-speaker dataset, supporting Hungarian text-to-speech conversion.
Downloads 21
Release Time : 5/13/2023
Model Overview
This model is a VITS-based Hungarian single-speaker TTS model capable of converting Hungarian text into natural speech.
Model Features
High-Quality Hungarian Speech Synthesis
Trained on 10 hours of high-quality Hungarian speech data, generating natural and fluent speech.
Single Speaker Characteristics
The model learns and preserves the vocal characteristics and pronunciation style of a single speaker.
Efficient Training
Training completes in just 3 days on an RTX 3090 GPU with a batch size of 16.
Model Capabilities
Hungarian Text-to-Speech
Single Speaker TTS
Use Cases
Speech Synthesis Applications
Audiobook Production
Automatically convert Hungarian text into speech for audiobook production.
Generates speech close to the quality of original recordings
Voice Assistants
Provides natural speech output capabilities for Hungarian voice assistants.
Featured Recommended AI Models