Stars
Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.
AuraSR: GAN-based Super-Resolution for real-world
Bringing BERT into modernity via both architecture changes and scaling
Python tool for converting files and office documents to Markdown.
Console Interface and Library to remove silent parts of a media file 🔈
A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
Automate browser-based workflows with LLMs and Computer Vision
A template project for easily converting Claude AI’s Artifacts into React applications, ready to run out of the box or extend as needed.
Fast and accurate automatic speech recognition (ASR) for edge devices
Share a single, easily-switchable application window on a projector on macos
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
This repo is for the SPL paper "Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap"
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Entropy Based Sampling and Parallel CoT Decoding
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper