whatmodel.sh / stt / Fun-ASR-MLT-Nano-2512

Fun-ASR-MLT-Nano-2512

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Fun-ASR-MLT-Nano-2512 is an open-weights speech-to-text model from Alibaba (FunAudioLLM), released December 2025. Its published size is 0.83B parameters. Licence: apache-2.0.

Catalogue identity notes

FunAudioLLM/Fun-ASR-MLT-Nano-2512: multilingual (MLT) variant of Fun-ASR-Nano-2512 (card model table 'Fun-ASR-MLT-Nano'). Distinct weights from fun-asr-nano-2512 (transcribe.cpp scores both). Port pins upstream cf67a93 (2025-12-23); later commits edit the card/install floor. Licence: card front matter apache-2.0.

Model information sources

Release date ↗ · Parameter count ↗

transcribe.cpp catalog 'params' 829,791,840 for its converted port of FunAudioLLM/Fun-ASR-MLT-Nano-2512@cf67a93 (no safetensors index on the Hugging Face repo).

57.0±3.5#54 of 162 speech-to-text modelsfrom 3 benchmark results across 1 source

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of Fun-ASR-MLT-Nano-2512, out of 176 with a score, then more from Alibaba (FunAudioLLM).

#modelscorewhereRAMreleased
61Whisper large-v3-turbo OpenAI57±1api $0.0005/audio min +local~2.4GB2024-10
62Omnilingual ASR LLM 3B Meta57±2local~11GB2025-11
63Fun-ASR-MLT-Nano-2512 Alibaba (FunAudioLLM)57±4local~0.9GB2025-12
64Parakeet Redux Moondream57±4local~0.2GB2026-09
65Parakeet TDT 0.6B v3 NVIDIA57±1api $0.0015/audio min +local~2GB2025-08
more from Alibaba (FunAudioLLM)
80Fun-ASR-Nano-2512 Alibaba (FunAudioLLM)55±3local~0.9GB2025-12
133SenseVoice Small Alibaba (FunAudioLLM)46±3local~0.3GB2024-07

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 95% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER1.7% ✎▁···▁▁▂·▄▄██ beats 38/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%blunt
FLEURS English test WER4.9% ✎▁··▁▁▁▁▁▁▃█▁ beats 25/56avg 5.8%▇▇▇▇▇▇▇▇▇ 21%blunt
FLEURS Mandarin test error rate8.6% ✎▂▂··▂▄▂▂·▆██ beats 11/17avg 12%▇▇▇▇▇▇▇▇ 20%typical

$ where to run it

Other ways to run it

  1. Run it as published · needs ~0.89 GB · from github.com/handy-computer
    git clone https://github.com/handy-computer/transcribe.cpp.git && cd transcribe.cpp && cmake -B build && cmake --build build && hf download handy-computer/Fun-ASR-MLT-Nano-2512-gguf Fun-ASR-MLT-Nano-2512-Q8_0.gguf --local-dir models/fun-asr-mlt-nano-2512 && build/bin/transcribe-cli -m models/fun-asr-mlt-nano-2512/Fun-ASR-MLT-Nano-2512-Q8_0.gguf audio.wav

Official weights and documentation: huggingface.co/FunAudioLLM ↗

$ how the score was worked out · transcribe.cpp model catalog… 95%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%MIT
prior · pull toward the middle▇ 5%
weighted average= 57.0

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json