Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

🔊 Text-Prompted Generative Audio Model

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

A multi-voice TTS system trained with an emphasis on quality

High-Resolution Image Synthesis with Latent Diffusion Models

Foundational Models for State-of-the-Art Speech and Text Translation

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Flax is a neural network library for JAX that is designed for flexibility.

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Puzzles for learning Triton

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

Fast parallel LLM inference for MLX

Bare-bones implementations of some generative models in Jax: diffusion, normalizing flows, consistency models, flow matching, (beta)-VAEs, etc

Minimal, lightweight JAX implementations of popular models.

Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.

Repository for fine-tuning Transformers 🤗 based seq2seq speech models in JAX/Flax.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

This is a port of Mistral-7B model in JAX

A set of TFDS dataset builders for common datasets

A novel Disfluency Correction & Machine translation Dataset for English, Hindi, German and French