Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
readme: replace SVG banner with value-first header (code demo + badges + one-liner)
游雁6f0778d3063e
diff --git a/README.md b/README.mdindex 996f0944e..014452458 100644--- a/README.md+++ b/README.md@@ -1,19 +1,31 @@-[//]: # '<div align="left"><img src="docs/images/funasr_logo.jpg" width="400"/></div>'+<div align="center">-([简体中文](./README_zh.md)|English)+# FunASR-[//]: # "# FunASR: A Fundamental End-to-End Speech Recognition Toolkit"--[](https://github.com/Akshay090/svg-banners)+**Speech Understanding in One API Call**[](https://pypi.org/project/funasr/)+[](https://github.com/modelscope/FunASR)+[](https://pypi.org/project/funasr/)+[](LICENSE)++[English](./README.md) | [简体中文](./README_zh.md) | [Docs](https://modelscope.github.io/FunASR/) | [Benchmark](https://modelscope.github.io/FunASR/benchmark.html)++</div>++> **170x realtime** on GPU · **50+ languages** · **Speaker diarization** · **Emotion detection** — all in 3 lines of Python.++```python+from funasr import AutoModel+model = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda")+result = model.generate(input="meeting.wav")+# → Timestamped text with speaker labels, punctuation, and emotion tags+```<p align="center"><a href="https://trendshift.io/repositories/3839" target="_blank"><img src="https://trendshift.io/api/badge/repositories/3839" alt="modelscope%2FFunASR | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a></p>-<strong>FunASR</strong> hopes to build a bridge between academic research and industrial applications on speech recognition. By supporting the training & finetuning of the industrial-grade speech recognition model, researchers and developers can conduct research and production of speech recognition models more conveniently, and promote the development of speech recognition ecology. ASR for Fun!-[**Highlights**](#highlights)| [**Benchmark**](#benchmark)| [**News**](https://github.com/alibaba-damo-academy/FunASR#whats-new)