Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
All in one Qwen3-ASR Server, compatible with OpenAI API
| Date | Stars |
|---|---|
| 2026-07-31 | 323 |
| 2026-08-03 | 326 |
| 2026-08-05 | 329 |
| 2026-08-06 | 329 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
35.0
growth rate 0.00%/day
<div align="center"> <h1>Qwen3-ASR</h1> <h3>Ready-to-use Local Speech Recognition API Service</h3> Speech recognition API service centered on [Qwen3-ASR](https://github.com/QwenLM/Qwen3-ASR), with CUDA vLLM and CPU Rust backends, OpenAI API compatibility, Alibaba Cloud Speech API compatibility, and a Paraformer realtime websocket capability. [简体中文](./docs/README_zh.md) ---    </div> ## Live Demo Site - **Web Demo**: https://asr.vect.one ## Demo [](https://media.cdn.vect.one/qwenasr_client_demo.mp4) ## Contact Author - **Email**: [[email protected]](mailto:[email protected]) - **WeChat**: <img src="./demo/contact.jpg" alt="WeChat QR code" width="220"> ## Release 1.0.3 > `v1.0.3` removes the voiceprint database and sqlite-vec dependency, unifies > offline deployment under `HF_HUB_OFFLINE`, and reduces the default deployment > configuration to the settings in `.env.example`. > > `v1.0.0` introduced a large breaking refactor relative to the earlier `main` branch. > If you are upgrading from `main`, read the release notes before reusing old deployment assumptions. > > Key breaking changes: > - Python dependency management is now `uv`-based (`pyproject.toml` + `uv.lock`); `requirements*.txt` are gone > - Runtime stack changed to `CUDA -> official vLLM`, `CPU/macOS -> vendored QwenASR Rust` > - `MLX` / Apple Silicon GPU path has been removed; `mps` is normalized to `cpu` > - macOS / Apple Silicon now defaults to `qwen3-asr-0.6b`; set `QWEN3_ASR_MODEL` to override it > - `ENABLED_MODELS` has been removed > - Voiceprint APIs and persistent speaker identity matching have been removed > ## Features - **Hybrid Runtime Stack** - Uses auto-selected Qwen3-ASR for offline inference and Paraformer realtime for websocket streaming - **Speaker Diarization** - Automatic multi-speaker identification using CAM++ model - **OpenAI API Compatible** - Supports `/v1/audio/transcriptions` endpoint, works with OpenAI SDK - **Alibaba Cloud API Compatible** - Supports Alibaba Cloud Speech RESTful API and WebSocket streaming protocol - **WebSocket Streaming** - Real-time streaming speech recognition with low latency - **Smart Far-Field Filtering** - Automatically filters far-field sounds and ambient noise in streaming ASR - **Intelligent Audio Segmentation** - VAD-based greedy merge algorithm for automatic long audio splitting - **GPU Batch Processing** - Batch inference support, 2-3x faster than sequential processing - **Resource-Aware Runtime** - Auto-selects the appropriate Qwen3-ASR model for the current machine ## Acknowledgements - [Qwen3-ASR](https://github.com/QwenLM/Qwen3-ASR) provides the official model family and multimodal/vLLM usage guidance - [QwenASR](https://github.com/huanglizhuo/QwenASR) provides the CPU Rust backend vendored by this project ## Quick Deployment ### 1. Docker Deployment (Recommended) ```bash # Copy and edit configuration cp .env.example .env # Edit .env to set API_KEY (optional) # Start service (GPU version) docker-compose up -d # Or CPU version docker-compose -f docker-compose-cpu.yml up -d # Multi-GPU auto mode (one instance per visible GPU) CUDA_VISIBLE_DEVICES=0,1,2,3 docker-compose up -d ``` Service URLs: - **API Endpoint**: `http://localhost:17003` - **API Docs**: `http://localhost:17003/docs` **docker run (alternative):** ```bash # GPU version docker run -d --name qwen3-asr \ --gpus all \ -p 17003:8000 \ -e CUDA_VISIBLE_DEVICES=0,1,2,3 \ -e API_KEY=your_api_key \ -v ./models/modelscope:/root/.cache/modelscope \ -v ./models/huggingface:/root/.cache/huggingface \ -v ./data:/app/data \ quantatrisk/qwen3-asr:gpu-latest # CPU version docker run -d --name qwen3-asr \ -p 17003:8000 \
Excerpt of 17,479 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:61484b36f2655f98, topic:asr