T

Tts Transformer Zh Cv7 Css10

Developed by facebook
A Transformer-based text-to-speech model built on fairseq S^2, supporting Simplified Chinese with a single female voice, trained on Common Voice v7 and CSS10 datasets.
Downloads 15
Release Time : 3/2/2022

Model Overview

This is a Transformer-based text-to-speech (TTS) model specifically optimized for Simplified Chinese, using a single female voice for speech synthesis. The model was pre-trained on the Common Voice v7 dataset and fine-tuned on the CSS10 dataset.

Model Features

Transformer-based architecture
Utilizes advanced Transformer architecture to deliver high-quality speech synthesis
Chinese speech synthesis
A speech synthesis model specifically optimized for Simplified Chinese
Single female voice
Uses a single female voice for consistent timbre in speech synthesis
Multi-dataset training
Pre-trained on Common Voice v7 and fine-tuned on CSS10 to enhance speech quality

Model Capabilities

Text-to-speech
Chinese speech synthesis
High-quality speech generation

Use Cases

Voice interaction
Voice assistants
Provides natural voice output for Chinese voice assistants
Generates natural and fluent Chinese speech
Audiobooks
Converts Chinese text into speech for audiobook production
Produces clear and audible Chinese narration
Assistive technology
Visual impairment assistance
Offers text-to-speech services for visually impaired individuals
Helps visually impaired individuals access textual information
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase