Open-source projects tagged “deep-learning”

A lightweight zipvoice-based text-to-speech model for voice cloning, generating 48kHz speech at up to 150x realtime on GPU.

Open-source native vision-language models (NEO series) that process pixels and words in one encoder-free dense architecture, with 2B and 9B releases.

Open-source toolkit from Unity that lets games and simulations serve as environments for training AI agents with reinforcement and imitation learning.

Python SDK client for Nixtla's TimeGPT, a hosted foundation model for time series forecasting and anomaly detection that runs via API.

A video LLM trained with streaming speech transcription so it can produce real-time commentary on video, with Gradio and CLI demos.

A collection of 419 pre-trained AI models covering vision, speech, NLP, and LLMs, each runnable from a simple CLI with automatic weight download.

A PyTorch-based blind face restoration model that repairs degraded, low-quality, or old face photos using a codebook lookup transformer.

A short introductory book on reinforcement learning, with PyTorch implementations of the algorithms it covers from MC to PPO.

An open-source Python OCR library that detects and recognizes text in PDFs and images using deep learning models built on PyTorch.

A 12-chapter, commented tutorial that walks through building and training a LLaMA-style GPT language model from scratch in Python and PyTorch.

A learn-by-building ML course: a from-scratch NumPy deep learning framework (CLI) plus 350+ browser-based coding questions.

A curated Markdown knowledge base of 923 ML papers, lectures and articles, plus a small NumPy-only custom classifier and regressor called APRL.

A PyTorch-based open-source framework for deep learning on healthcare imaging data, covering preprocessing, networks, losses and metrics.

YuE2 is an open music generation model that writes an editable melody-and-chord score from lyrics and a style prompt, then renders it as a full song with vocals.