Make text LLMs listen and speak

A simple, extendable, and clean backtesting framework for portfolio allocation problems (and more).

A dialect of Lisp that's embedded in Python

Fast inference engine for Transformer models

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

Speech To Speech: an effort for an open-sourced and modular GPT4-o

An interactive explorer for single-cell transcriptomics data

a model manager for downloading huggingface datasets over s3 / ipfs

Distributed Training Over-The-Internet

Fast and accurate automatic speech recognition (ASR) for edge devices

AI-powered markdown editor - leverage LLMs with your documents - 100% local or in the cloud

Productive, portable, and performant GPU programming in Python.

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

Finetune VITS and MMS using HuggingFace's tools

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

An autoregressive character-level language model for making more things

End-to-End Neural Diarization

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

ASR (Automatic Speech Recognition) for real-time streamed audio powered by Whisper and tranformers

Joint speech-language model - respond directly to audio!

Joint speech-language model - respond directly to audio!

A fast multimodal LLM for real-time voice

Tools for merging pretrained large language models.

A @ClickHouse fork that supports high-performance vector search and full-text search.

Scalable data pre processing and curation toolkit for LLMs

Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

An awesome repository of local AI tools

Official repository for GDC User Guides in Markdown format