Production First and Production Ready End-to-End Speech Recognition Toolkit

Port of OpenAI's Whisper model in C/C++

DoctorGPT is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.

Inference code for LLaMA models

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Package for aligning audio files through audio fingerprinting

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

NVIDIA device plugin for Kubernetes

Tools for handling speech data in machine learning projects.

Long audio alignment using Kaldi