Multi-backend whisper app. Blazing fast. Mac-arm optimized. Easy install. Input a local file or url and this service will transcribe it using Whisper AI. Completely private and Free 🤯🤯🤯
- cli
- diarization
- python
- speech-to-text
132,218 visible repositories in the index
1,729–1,752 of 4,797 · Most stars
Multi-backend whisper app. Blazing fast. Mac-arm optimized. Easy install. Input a local file or url and this service will transcribe it using Whisper AI. Completely private and Free 🤯🤯🤯
CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).
Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.
一个批量转存、分享和下载夸克网盘文件的工具,可以快速地将大量分享文件转存到到自己的网盘内,或者将网盘文件批量生成分享链接
A terminal-based dashboard for managing cron jobs locally and on servers.
Fast and customizable framework for automatic ML model creation (AutoML)
A toolkit for time series machine learning and deep learning
Production-grade retries for Python
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
A source-backed catalog of Meta Muse integrations and community connector skills, with capability, authentication, and permission notes.
Print awesomely in terminals.
SSH-MITM - ssh audits made simple
Run TUIs and terminals in your browser
Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.
PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.
OpenStack Networking (Neutron). Mirror of code maintained at opendev.org.
Generates millions of keyword-based password mutations in seconds.
Streaming 3D reconstruction from only video input: Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
Clone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT:gpt-image-2 仿版式、你换内容,另含 10 套精选风格。Claude Code / OpenClaw skill.
Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
记录自己编写、修改的部分工具
The python3 version of the automated Comic Book downloader (cbr/cbz) for use with various download clients.