whatmodel.sh / stt / Fun-ASR-Nano-2512
Fun-ASR-Nano-2512
↗ share
+ contribute
Fun-ASR-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-Nano-2512 (Tongyi Lab end-to-end ASR; card: Chinese, English and Japanese; 'Model Size 0.8B'). Open-weights nano model, distinct from the hosted fun-asr-flash (catalogued) and from Fun-ASR-MLT-Nano-2512. transcribe.cpp port pins upstream a7088d6 (2025-12-23); later commits are card/docs edits per their titles. Licence: card front matter apache-2.0 (added 2026-05-25).
Model information sources
Release date ↗ · Parameter count ↗
transcribe.cpp catalog 'params' 829,791,840 for its converted port of FunAudioLLM/Fun-ASR-Nano-2512@a7088d6 (no safetensors index on the Hugging Face repo).
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-Nano-2512, out of 176 with a score, then more from Alibaba (FunAudioLLM).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 78 |  Omnilingual ASR LLM 3B v2 | 56±3 | local | ||
| 79 |  LiteWhisper large-v3 | 55±3 | local | ||
| 80 | Fun-ASR-Nano-2512 | 55±3 | local | ||
| 81 |  Scribe v2 Realtime | 55±3 | api $0.0065/audio min | ||
| 82 | LiteWhisper large-v3-acc | 55±3 | local | ||
| more from Alibaba (FunAudioLLM) | |||||
| 63 | Fun-ASR-MLT-Nano-2512 | 57±4 | local | ||
| 133 | SenseVoice Small | 46±3 | local | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
other tests5 not in a task · 97% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LibriSpeech test-clean WER +1 | 1.8% ✎ | ▁···▁▁▂·▄▄██ beats 37/56 | 36% |
| LibriSpeech test-other WER | 4.0% ✎ | ███·····██·█ beats 3/5 | 18% |
| FLEURS English test WER +1 | 5.5% ✎ | ▁··▁▁▁▁▁▁▃█▁ beats 21/56 | 17% |
| FLEURS Mandarin test error rate +1 | 8.6% ✎ | ▂▂··▂▄▂▂·▆██ beats 12/17 | 17% |
| VoxPopuli English test WER | 6.5% ✎ | ▄··▄··▄···█▄ beats 2/5 | 8.5% |
$ where to run it
Other ways to run it
- 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-Nano-2512-gguf Fun-ASR-Nano-2512-Q8_0.gguf --local-dir models/fun-asr-nano-2512 && build/bin/transcribe-cli -m models/fun-asr-nano-2512/Fun-ASR-Nano-2512-Q8_0.gguf audio.wav
Official weights and documentation: huggingface.co/FunAudioLLM ↗
$ how the score was worked out · transcribe.cpp model catalog… 55%, microsoft/VibeVoice-ASR-BitNe… 42%
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
| source | results | share of the score |
|---|---|---|
 transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports | 3 | 55% |
 microsoft/VibeVoice-ASR-BitNet model card (Accuracy table) | 5 | 42% |
| prior · pull toward the middle | 3% | |
| weighted average | = 55.4 |
$ improve this page
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