Making large AI models cheaper, faster and more accessible
- deep-learning
- hpc
- large-scale
- data-parallelism
47,133 repositories indexed
1–12 of 12 · Most stars
Making large AI models cheaper, faster and more accessible
OpenMMLab Detection Toolbox and Benchmark
Faster Whisper transcription with CTranslate2
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
High level network definitions with pre-trained weights in TensorFlow
Build fully-functioning computer vision models with PyTorch
Face detection using deep learning.
Friendly Environment for Neural Networks (fenn) is a simple Python framework for building ML/DL workflows and LLM agents faster, with prebuilt trainers, agent templates, logging, configuration management, and much more.
Python3 script that transfers files in Google Colab 10-50x faster, using multi-threaded parallel copying between Google Drive locations.