Automatic Speech Recognition on WenetSpeech Meeting domain (ws-meeting)
4.32CERFireRedASR2-LLM
Evaluation results
| Method | Links | |
|---|---|---|
| FireRedASR2-LLMParameters=8B+, Streaming setting=non-streaming2026.03 | 4.32 | |
| FireRedASR2-AEDParameters=1B+, Streaming setting=non-streaming2026.03 | 4.53 | |
| Doubao-ASRType=commercial API, Streaming setting=non-streaming, ITN and punctuation setting=disabled, VAD configuration=default2026.03 | 4.74 | |
| Fun-ASRType=commercial API, Streaming setting=non-streaming, ITN and punctuation setting=disabled, VAD configuration=default2026.03 | 5.78 | |
| Qwen3-ASRType=open-source checkpoint, Streaming setting=non-streaming2026.03 | 5.88 |