1 مستودع
Toolkits for managing the iterative process of training and fine-tuning neural speech models.
Distinct from Speech Synthesis Models: Focuses on the trainer framework rather than the resulting speech synthesis model architecture.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Training Frameworks. Refine with filters or upvote what's useful.
This project is a comprehensive suite for neural speech synthesis, featuring a deep learning text-to-speech engine, a neural speech synthesis trainer, and a voice cloning toolkit. It provides a system for synthesizing human-like speech from text using neural network models and high-fidelity vocoders. The suite includes a speech model conversion utility to transform deep learning models between different formats for deployment across various hardware runtimes. It also provides a self-contained HTTP server to expose pre-trained text-to-speech models as a remote audio API. Capabilities include
Ships a framework for training and fine-tuning speech models using custom datasets and hardware acceleration.