Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Repository Index
142,273 visible repositories in the index
553–576 of 2,392 · Most stars
Repositório criado com intuito de reunir informações, fontes(websites/portais) e tricks de OSINT dentro do contexto Brasil.
- osint
- brasil
- hacking
- threat-intelligence
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.
Deforum extension for AUTOMATIC1111's Stable Diffusion webui
- animations
- automatic1111
- plugin
- stable-diffusion
Easily turn your Click CLI into a powerful terminal application
Optical character recognition for Japanese text, with the main focus being Japanese manga
- ocr
- japanese
- manga
- transformers
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
- claude-code
- codex
- data-processing
- harness-engineering
🌊 A Human-in-the-Loop workflow for creating HD images from text
- dalle
- generative-art
- human-in-the-loop
- jina
Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.
Plugin for some git integration into sublime text
Convert HTML to Markdown-formatted text.
Extensible memoizing collections and decorators
🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp
Translated说人话 (Shuorenhua, "speak plainly") | Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT — removes AI tone, preserves facts, handles different scenarios separately, and the rewritten text can be sent directly.
- ai-writing
- anti-slop
- chatgpt
- chinese
[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy
- interactive
- object-counting
- object-detection
- open-set
OpenTelemetry Python API and SDK
- python
- opentelemetry
- tracecontext
- correlationcontext
Cross-platform CLI and Python drivers for AIO liquid coolers and other devices
- corsair
- evga
- nzxt
- liquid-cooler
A curated collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.
Deep neural network to extract intelligent information from invoice documents.
- invoice
- invoice-management
- invoices
- invoice-insight
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
- face
- flux
- identity-preserving
- image-editing
Make videos with Claude Code: script, AI voiceover, music, video clips and render, on open-source models that cost cents
- ai-video-generator
- claude-code
- developer-tools
- elevenlabs
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
- fine-tuning-llm
- large-language-models
- long-context
- llm