Efficient LLM Inference over Long Sequences

Normalized Transformer (nGPT)

A project to improve skills of large language models

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

🔊 Text-Prompted Generative Audio Model

🦜🔗 Build context-aware reasoning applications

A Generative Flow for Text-to-Speech via Monotonic Alignment Search

Automatically exported from code.google.com/p/cuda-convnet2

Data manipulation and transformation for audio signal processing, powered by PyTorch

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

AIStore: scalable storage for AI applications

An Open Source Machine Learning Framework for Everyone

Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.

OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research

Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

End-to-end speech recognition using TensorFlow

Why Momentum Really Works