1 repository
Building specialized runtime engines for transformer-based speech models to increase execution speed.
Distinct from Inference Performance Optimization: Specifically targets the creation of TensorRT engines for speech transformers
Explore 1 awesome GitHub repository matching artificial intelligence & ml · TensorRT-LLM Engine Optimization. Refine with filters or upvote what's useful.
F5-TTS is a text-to-speech system that utilizes a flow matching engine and diffusion transformers to generate fluent synthetic speech. It functions as a multilingual speech synthesizer and neural training framework, providing tools for voice cloning and high-performance inference serving. The project distinguishes itself through a voice cloning toolkit capable of mimicking specific speaker characteristics and tones from reference audio clips. It supports cross-lingual generation, allowing for the synthesis of audio across various global languages or the mixing of multiple languages within a s
Optimizes transformer and whisper models using TensorRT-LLM to increase inference execution speed.