{"data":{"slug":"modelscope-funasr","name":"FunASR","tagline":"Industrial-grade speech recognition toolkit","github_url":"https://github.com/modelscope/FunASR","owner":"modelscope","repo":"FunASR","owner_avatar_url":"https://avatars.githubusercontent.com/u/109945100?v=4","primary_language":"Python","stars":19554,"forks":1965,"topics":["asr","audio","chinese","emotion-recognition","funasr","mcp-server","multilingual-asr","openai-compatible-api","paraformer","punctuation","pytorch","real-time-asr","speaker-diarization","speech-recognition","speech-to-text","streaming-asr","transcription","vllm","voice-activity-detection","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-30T01:45:38+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/modelscope-funasr","markdown_url":"https://www.graphcanon.com/tools/modelscope-funasr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/modelscope-funasr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=modelscope-funasr","description":"Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.","homepage_url":null,"license":"MIT","open_issues":5,"watchers":114,"ai_summary":"FunASR is an industrial-grade speech recognition software with real-time capabilities, support for over 50 languages, and features like speaker diarization and emotion detection.","readme_excerpt":"## Quick Start\n\n\n\nNo local setup? Open the [Colab quickstart](./examples/colab/) to transcribe a public sample or upload your own audio in a browser.\n\n```bash\n\n---\n\n## Installation\n\n```bash\npip install funasr\n```\n\n<details><summary>From source / Requirements</summary>\n\n```bash\ngit clone https://github.com/modelscope/FunASR.git && cd FunASR\npip install -e ./\n```\nRequirements: Python ≥ 3.8. Install PyTorch + torchaudio first ([pytorch.org](https://pytorch.org/get-started/locally/)), then `pip install funasr`.\n\n</details>\n\n---\n\n---\n\n# Docker streaming service\ndocker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12\n```\n\n---\n\n## License\n\n- FunASR toolkit source code in this repository: [MIT License](./LICENSE).\n- Pretrained model weights are licensed separately. Check the license shown on each model card; when a model card links to the [FunASR Model Open Source License Agreement](./MODEL_LICENSE), those terms apply.","github_created_at":"2022-11-24T02:28:11+00:00","created_at":"2026-07-11T12:14:05.101904+00:00","updated_at":"2026-08-16T04:01:49.581277+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"asr","name":"asr"},{"slug":"audio","name":"audio"},{"slug":"chinese","name":"chinese"},{"slug":"emotion-recognition","name":"emotion-recognition"},{"slug":"multilingual-asr","name":"multilingual-asr"},{"slug":"openai-compatible-api","name":"openai-compatible-api"},{"slug":"speech-recognition","name":"speech-recognition"},{"slug":"speech-to-text","name":"speech-to-text"}],"trust":{"provenance":{"is_fork":false,"github_id":569959091,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-30T06:00:28.223Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-07-27T15:26:00Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-08-16T04:01:49.207Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-30T06:00:28.658Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-30T06:00:28.658Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-30T06:00:28.658Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Python ≥ 3.8.","PyTorch and torchaudio must be installed separately before running FunASR."],"min_ram_gb":null,"requires_docker":false},"constraints":{"runtime":"unknown","min_ram_gb":null,"requires_docker":false},"when_to_use":["When requiring high-speed real-time processing of up to 170x realtime speech recognition.","For projects that involve emotion detection or speaker diarization alongside transcription.","If integration with OpenAI-compatible APIs is necessary for further processing."],"when_not_to_use":["In scenarios where only a narrow set of languages are required, as overhead for supporting over 50 languages may be unnecessary.","For projects lacking GPU resources since certain models, like the Fun-ASR-Nano flagship model, require a GPU to run effectively."],"source":"enrich:decision_facts","observed_at":"2026-07-17T05:08:59.991Z"},"constraint_facets":{"runtime":"unknown","min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires Python ≥ 3.8.; PyTorch and torchaudio must be installed separately before running FunASR."},{"label":"Adopt for","value":"FunASR is an industrial-grade toolkit supporting real-time speech recognition across over 50 languages."},{"label":"License detail","value":"MIT License allows free use and modification."},{"label":"Runtime","value":"unknown"}]}}