WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
Repository Index
47,133 repositories indexed
25–34 of 34 · Most stars
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.
Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.
- cpp
- ggml
- gguf
- metal
TranslatedA Bilibili command-line tool designed for AI Agents: QR code login, watching videos, commenting, direct messages, posting updates, uploading videos, all with JSON output
- agent-skills
- ai-agent
- automation
- bilibili
Lightweight, powerful real-time speech translation with multilingual support and a multilingual UI.
- asr-model
- translation
- audio-to-text
- crispasr
Fast fork of llama.cpp designed for Qwen3.8-Flash-Next
An NES CPU compiled into the weights of a stock Qwen3.5 model
Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python.
- asr
- local-ai
- offline
- portable
An LLM running on an NPU inside an LLM. Karpathy's stories260K writing stories on a vector unit compiled into Qwen3.5-4B's weights.
🔮 MAGUS Council: World's first? 4-AI consultation system (Gemini+Claude+GPT-5+Qwen) in VS Code - Revolutionary multi-agent development environment