Automatic Speech Recognition on 24 public ASR Avg-All-24 (test)
9.67CERFireRedASR2-LLM
Evaluation results
| Method | Links | |
|---|---|---|
| FireRedASR2-LLMParameters=8B+, Streaming setting=non-streaming2026.03 | 9.67 | |
| FireRedASR2-AEDParameters=1B+, Streaming setting=non-streaming2026.03 | 9.8 | |
| Qwen3-ASRType=open-source checkpoint, Streaming setting=non-streaming2026.03 | 10.12 | |
| Fun-ASRType=commercial API, Streaming setting=non-streaming, ITN and punctuation setting=disabled, VAD configuration=default2026.03 | 10.92 | |
| Doubao-ASRType=commercial API, Streaming setting=non-streaming, ITN and punctuation setting=disabled, VAD configuration=default2026.03 | 12.98 |