Automatic Speech Recognition on Avg-Mandarin-4 (test)
2.89CERFireRedASR2-LLM
Evaluation results
| Method | Links | |
|---|---|---|
| FireRedASR2-LLMParameters=8B+, Streaming setting=non-streaming2026.03 | 2.89 | |
| FireRedASR2-AEDParameters=1B+, Streaming setting=non-streaming2026.03 | 3.05 | |
| Doubao-ASRType=commercial API, Streaming setting=non-streaming, ITN and punctuation setting=disabled, VAD configuration=default2026.03 | 3.69 | |
| Qwen3-ASRType=open-source checkpoint, Streaming setting=non-streaming2026.03 | 3.76 | |
| Fun-ASRType=commercial API, Streaming setting=non-streaming, ITN and punctuation setting=disabled, VAD configuration=default2026.03 | 4.16 |