All tasks / Models
Fun-ASR-Nano-2512
Alibaba's small open-weights speech recognition model, the open sibling of the Fun-ASR API.
- Alibaba (FunAudioLLM)
- Open weights
- Released Dec 2025
Where it ranks
- BTranscriptionModels · Local · 7.2% on Hugging Face Open ASR Leaderboard (English, short-form average WER) (secondary benchmark)
Facts
- Vendor
- Alibaba (FunAudioLLM)
- Family
- Fun-ASR-Nano
- Released
- Dec 2025
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.83B
- GPU memory to run locally
- ~2 GB (Derived: about 0.83B parameters is roughly 1.7 GB of bf16 weights plus runtime overhead; not an official requirement.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Hugging Face Open ASR Leaderboard (English, short-form average WER) | 7.2% | FunAudioLLM/Fun-ASR-Nano-2512-hfAverage WER over the board's default datasets (English short-form, version 17-10-2026); rank 39 of 56; read from the Space's /config table data. | 17 Oct 2026 | huggingface.co |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.