Stars
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
A universal package of scraper scripts for humans
frecklebars / Ryven
Forked from leon-thomm/RyvenFlow-based visual scripting for Python including a machine learning package
Official implementation of the papers "GECToR – Grammatical Error Correction: Tag, Not Rewrite" (BEA-20) and "Text Simplification by Tagging" (BEA-21)
A fast, low-resource Natural Language Processing and Text Correction library written in Rust.
Interactive Data Visualization in the browser, from Python
Espresso: A Fast End-to-End Neural Speech Recognition Toolkit
An Earley-Algorithm Context-free grammar Parser Toolkit
DDlog is a programming language for incremental computation. It is well suited for writing programs that continuously update their output in response to input changes. A DDlog programmer does not w…
Fungi: Typed incremental computation with names
MessagePack-RPC is an inter-process messaging library that uses MessagePack for object serialization.
Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time
A checklist for incorporation so you can get back to building your product, fundraising, etc.
Presenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.
Python library and shell utilities to monitor filesystem events.
Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.
Safe code refactoring for modern Python.
torch-optimizer -- collection of optimizers for Pytorch
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Adlik: Toolkit for Accelerating Deep Learning Inference
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while control…
DeepOBS: A Deep Learning Optimizer Benchmark Suite
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries