Integrate cutting-edge LLM technology quickly and easily into your apps

🔊 Text-Prompted Generative Audio Model

Easily train a good VC model with voice data <= 10 mins!

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Causal depthwise conv1d in CUDA, with a PyTorch interface

A suite of speech signal processing tools

DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported …

GUI for a Vocal Remover that uses Deep Neural Networks.

Development repository for the Triton language and compiler

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Mamba SSM architecture

Lightweight signal processing library for audio and speech applications

An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

SoftVC VITS Singing Voice Conversion

Onnx wrapper for espnet infrernce model

End-to-End Speech Processing Toolkit

Pre-trained Deep Learning models and demos (high quality and extremely fast)

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

A high-quality speech analysis, manipulation and synthesis system

ICASSP 2023 Accepted

Low Level Speech Model (version 2.1) for high quality speech analysis-synthesis