{"v":1,"id":"model:hf:handy-computer/Fun-ASR-MLT-Nano-2512-gguf","slug":"model-handy-computer-fun-asr-mlt-nano-2512-gguf","kind":"model","category":"speech","title":"Fun-ASR-MLT-Nano-2512-gguf","summary":"Fun-ASR-MLT-Nano-2512: transcribe.cpp GGUF","source":{"provider":"hf","ref":"handy-computer/Fun-ASR-MLT-Nano-2512-gguf","url":"https://huggingface.co/handy-computer/Fun-ASR-MLT-Nano-2512-gguf","rev":"364640227abd3f786d139ac43b8ac1a98673989d","fetchedAt":"2026-10-02T21:00:22.523Z","etag":"W/\"233f-4v/g98op0L8YspFoHZ88CJrnDww\""},"author":{"name":"handy-computer","url":"https://huggingface.co/handy-computer"},"license":{"spdx":null,"raw":"other","url":"https://github.com/modelscope/FunASR/blob/main/MODEL_LICENSE","open":null,"note":"custom license: read it at the source before installing"},"metrics":{"downloads":33103,"downloadsWeek":15195,"likes":1,"takenAt":"2026-10-02T21:00:22.523Z"},"tags":["transcribe.cpp","gguf","asr","speech-to-text","fun-asr-nano","fun-asr-mlt-nano","sense-voice-encoder","qwen3","audio-llm","multilingual","automatic-speech-recognition","zh","en","yue","ja","ko","vi","id","th","ms","tl","ar","hi","bg","hr","cs","da","nl","et","fi","el","hu","ga","lv","lt","mt","pl","pt","ro","sk"],"pipeline":"automatic-speech-recognition","links":{"github":"ggml-org/whisper.cpp","npm":"nodejs-whisper"},"updatedAt":"2026-09-15T07:05:31.000Z","collectedAt":"2026-10-02T21:00:22.523Z","review":{"numbers":["33,103 downloads on Hugging Face","1 likes","license other","0.5 GB for Fun-ASR-MLT-Nano-2512-Q4_K_M.gguf","15,195 npm downloads a week for nodejs-whisper","latest nodejs-whisper@0.3.1"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T21:00:22.523Z","http":200},"description":"# Fun-ASR-MLT-Nano-2512: transcribe.cpp GGUF\n\nGGUF conversions of [FunAudioLLM/Fun-ASR-MLT-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512) for use\nwith [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).\n\nPorted from upstream commit\n[cf67a93](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512/commit/cf67a93),\npinned 2026-05-06.\nValidated against the FunASR reference at transcribe.cpp commit\n[f094d28](https://github.com/handy-computer/transcribe.cpp/tree/f094d28)\non 2026-05-06.\n\nOffline speech-to-text covering 31 languages, with focused optimization\non East and Southeast Asian languages: Chinese, English, Cantonese,\nJapanese, Korean, Vietnamese, Indonesian, Thai, Malay, Filipino, plus\nArabic, Hindi, and 19 European languages (Bulgarian, Croatian, Czech,\nDanish, Dutch, Estonian, Finnish, Greek, Hungarian, Irish, Latvian,\nLithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian,\nSwedish). Same architecture as Fun-ASR-Nano-2512 (~800M trainable\nparameters: frozen SenseVoiceEncoderSmall + 2-layer audio adaptor +\nbundled Qwen3-0.6B LLM); trained on a smaller multilingual corpus\n(\"hundreds of thousands of hours\" per the model card, vs Nano's\n\"tens of millions\"). Takes a 16 kHz mono WAV and emits text. Not\nstreaming, no translation, no timestamps. ITN (inverse text\nnormalization) is supported by the model and exposed via the\n`--itn` CLI flag and `transcribe_funasr_nano_params { use_itn }`\nin the library API.\n\n## Downloads\n\n| Quantization | Download | Size | WER (LibriSpeech test-clean) |\n| --- | --- | ---: | ---: |\n| BF16 | [Fun-ASR-MLT-Nano-2512-BF16.gguf](https://huggingface.co/handy-computer/Fun-ASR-MLT-Nano-2512-gguf/resolve/main/Fun-ASR-MLT-Nano-2512-BF16.gguf) | 1.67 GB | 1.74% |\n| F16 | [Fun-ASR-MLT-Nano-2512-F16.gguf](https://huggingface.co/handy-computer/Fun-ASR-MLT-Nano-2512-gguf/resolve/main/Fun-ASR-MLT-Nano-2512-F16.gguf) | 1.67 GB |…\n\nSource: https://huggingface.co/handy-computer/Fun-ASR-MLT-Nano-2512-gguf","install":{"kind":"model","hfId":"handy-computer/Fun-ASR-MLT-Nano-2512-gguf","gated":false,"format":"gguf","files":[{"name":"Fun-ASR-MLT-Nano-2512-BF16.gguf","size":1667504192,"quant":"BF16","sha256":"dcacaf5eb69651e4e3f1f79e9bdd16be518cf5f9ecaf023dada9c5aa891bde4b"},{"name":"Fun-ASR-MLT-Nano-2512-F16.gguf","size":1667504192,"quant":"F16","sha256":"ffd1e5258f2cfbc05dc3e467b570a32d5671a6511bcd070cd72f08657108213d"},{"name":"Fun-ASR-MLT-Nano-2512-Q4_K_M.gguf","size":556975168,"quant":"Q4_K_M","sha256":"9232584a27a7dcbcaf13640de8f9c2e7375178ea11e587f90a5328ecf06d58a1"},{"name":"Fun-ASR-MLT-Nano-2512-Q5_K_M.gguf","size":631129152,"quant":"Q5_K_M","sha256":"5906267c6067d254a2681f40d9eac70c4291ae14fb58ffea4c4cd22a307517ec"},{"name":"Fun-ASR-MLT-Nano-2512-Q6_K.gguf","size":690744384,"quant":"Q6_K","sha256":"e4ca67cbcb9b12c828b2afbadc871a8128ea3e73890d2747c687b1fac0ac6934"},{"name":"Fun-ASR-MLT-Nano-2512-Q8_0.gguf","size":891271232,"quant":"Q8_0","sha256":"d12476d8d9f2baa0ebf738fa955fa05ed33a654f1567289033a810c45d9d9002"}],"totalBytes":6105128320,"suggestedFile":"Fun-ASR-MLT-Nano-2512-Q4_K_M.gguf","requirements":{"ramGb":2,"diskBytes":556975168,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"],"command":"lsh models install hf:handy-computer/Fun-ASR-MLT-Nano-2512-gguf"}}