Open ASR · AMI-Cleaned WER ↗English short-form; normalization unversioned
10.35% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
FunAudioLLMDiscovered Oct 17, 2026
FunAudioLLM/Fun-ASR-Nano-2512-hf
0.83B parameters · 4 languages · Encoder: Qwen3-ASR · Decoder: Custom
Measured performance
All leaderboards ↗Benchmark results
Word error rate · lower is better
Open ASR · Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned
10.87% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Open ASR · Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned
8.41% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Open ASR · LS Clean WER ↗English short-form; normalization unversioned
1.47% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Open ASR · LS Other WER ↗English short-form; normalization unversioned
4.07% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Open ASR · SPGISpeech WER ↗English short-form; normalization unversioned
2.05% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Open ASR · URGENT2024 WER ↗English short-form; normalization unversioned
13.93% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Open ASR · Voice Arena Monsoon WER ↗English short-form; normalization unversioned
5.32% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Open ASR · Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned
3.4% WERFunAudioLLM/Fun-ASR-Nano-2512-hf
Access & cost
0 quotesPrices across providers
No listed provider price
Model specifications
- Developer
- FunAudioLLM
- Modality
- Audio
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Not reported
- First discovered
- Oct 17, 2026
Exact identities
- open-asr
FunAudioLLM%2FFun-ASR-Nano-2512-hf
Sources
Updated Oct 21, 2026