Tensors and Dynamic neural networks in Python with strong GPU acceleration
- neural-network
- autograd
- gpu
- numpy
132,241 visible repositories in the index
1–24 of 1,703 · Most stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
The open-source AI voice studio. Clone, dictate, create.
Open-Source Frontier Voice AI
TranslatedOCR software, free and offline. Open-source, free offline OCR software. Supports screenshots/batch importing of images, PDF document recognition, excluding watermarks/headers and footers, and scanning/generating QR codes. Has built-in multi-language libraries.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Easily train a good VC model with voice data <= 10 mins!
SGLang is a high-performance serving framework for large language models and multimodal models.
Instant voice cloning by MIT and MyShell. Audio foundation model.
Cross-platform, customizable ML solutions for live and streaming media.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Uncensored Open-source alternative to AI video platforms — Free AI image & video generation studio with 800+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.
FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.
You like pytorch? You like micrograd? You love tinygrad! ❤️
OpenMMLab Detection Toolbox and Benchmark
Privacy-first AI meeting note taker for Windows, macOS and Linux. Free, open source (MIT). On-device Whisper/Parakeet transcription and speaker diarization, no meeting bot. Open-source alternative to Granola, Otter and Fireflies. https://meetily.ai
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.