{"data":{"slug":"funaudiollm-fun-asr","name":"Fun-ASR","tagline":"Fun-ASR-Nano LLM-ASR model supports 31 languages for real-time speech recognition tasks","github_url":"https://github.com/FunAudioLLM/Fun-ASR","owner":"FunAudioLLM","repo":"Fun-ASR","owner_avatar_url":"https://avatars.githubusercontent.com/u/167062371?v=4","primary_language":"C","stars":1449,"forks":141,"topics":["31-languages","asr","audio","audio-language-model","chinese-dialects","fun-asr","fun-asr-nano","funasr","gguf","llama-cpp","llm-asr","multilingual-asr","on-device","pytorch","real-time-asr","speaker-diarization","speech-recognition","speech-to-text","transcription","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-24T13:50:47+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/funaudiollm-fun-asr","markdown_url":"https://www.graphcanon.com/tools/funaudiollm-fun-asr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/funaudiollm-fun-asr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=funaudiollm-fun-asr","description":"Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.","homepage_url":"https://huggingface.co/spaces/FunAudioLLM/Fun-ASR-Nano","license":"Apache-2.0","open_issues":0,"watchers":10,"ai_summary":"A multilingual ASR model that can handle dialects, accents, lyrics, hotwords, timestamps, and speaker diarization in real time across 31 different languages.","readme_excerpt":"### Install\n\n```bash\npip install \"funasr>=1.3.26\" \"vllm>=0.12.0\"\n```\n\n---\n\n## License\n\n- Source code in this repository is licensed under the [Apache License 2.0](./LICENSE).\n- Model weights are distributed separately and follow the license metadata on their model cards. The official [Fun-ASR-Nano](https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512) and [Fun-ASR-MLT-Nano](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512) cards currently list Apache-2.0; review the card for the specific artifact you download.","github_created_at":"2025-12-15T01:46:48+00:00","created_at":"2026-07-11T12:19:17.468082+00:00","updated_at":"2026-07-30T18:00:38.133194+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"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-language-model","name":"audio-language-model"},{"slug":"multilingual-asr","name":"multilingual-asr"},{"slug":"real-time-asr","name":"real-time-asr"},{"slug":"speaker-diarization","name":"speaker-diarization"},{"slug":"speech-to-text","name":"speech-to-text"}],"trust":{"provenance":{"is_fork":false,"github_id":1116516142,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-30T18:00:37.134Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":6,"days_since_push":6,"last_release_at":"2026-07-24T13:39:16Z"},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":26,"high_count":0,"last_scan_at":"2026-07-11T12:19:24.723Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-30T18:00:37.709Z"},"languages":{"value":["c"],"source":"github.language","observed_at":"2026-07-30T18:00:37.709Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-30T18:00:37.709Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms."},"requirements":{"notes":["Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need support for 31 different languages including handling of various dialects and accents.","For applications requiring real-time speech to text transcription that can also handle lyrics and hotwords."],"when_not_to_use":["Avoid if your project requires a specific programming language other than C as Fun-ASR is primarily developed in C.","If you do not require on-device processing, as this tool is designed for on-device inference which may limit scalability for cloud-based applications."],"source":"enrich:decision_facts","observed_at":"2026-07-17T02:12:14.815Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Open source under Apache License 2.0 allows free use with attribution and adherence to the license terms."},{"label":"Requirements","value":"Installation requires Python packages `funasr` version >=1.3.3, and `vllm` version >=0.12.0."},{"label":"Adopt for","value":"Fun-ASR is a real-time speech recognition tool supporting 31 languages with capabilities for handling dialects, accents, and speaker diarization."},{"label":"License detail","value":"Apache-2.0"}]}}