Stars
Benchmarking STT service TTFB and semantic WER for real-time AI applications
A toolkit to run Ray applications on Kubernetes
Fast, Flexible and Portable Structured Generation
Reference implementation: run any huggingface tokenizer in Android (rust).
Support PyTorch model conversion with LiteRT.
Efficient LLM Inference Acceleration using Prompting
Pitch perfect pointer positioning - a flute based mouse cursor controller
DataComp: In search of the next generation of multimodal datasets
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
A modern Python package and dependency manager supporting the latest PEP standards
An efficient video loader for deep learning with smart shuffling that's super easy to digest
Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…
Extract frames and motion vectors from H.264 and MPEG-4 encoded video.
Python bindings for FFmpeg - with complex filtering support
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
Minimalistic configs for git, vim, and zsh.
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
📊 A simple command-line utility for querying and monitoring GPU status
Visualizer for neural network, deep learning and machine learning models
Robust Speech Recognition via Large-Scale Weak Supervision
🥑 Language focused docker images, minus the operating system.
Unofficial GoPro WiFi API Documentation - HTTP GET requests for commands, status, livestreaming and media query.