ibm-granite/granite-speech-4.1-2b-plus
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| WER MLS | speech-asr | 34.3 | low | | Qwen3-FA [2] | 48.1 | 82.5 | 27.8 | 29.3 | **41.0** | 48.4 | 34.3 | 29.9 | 42.7 | **38.1** | 27.0 | **31.2** | **26.3** | 30.3 | 40.0 | 29.4 | 34.2 | 33.3 | | |
| WER GigaSpeech | speech-asr | 9.8 | high | | ibm-granite/granite-speech-4.1-2b | 5.33 | 8.09 | 8.37 | 9.8 | 1.33 | 2.5 | 3.78 | 3.07 | 5.7 | | |
| WER Earnings-22 | speech-asr | 8.37 | high | | ibm-granite/granite-speech-4.1-2b | 5.33 | 8.09 | 8.37 | 9.8 | 1.33 | 2.5 | 3.78 | 3.07 | 5.7 | | |
| WER AMI | speech-asr | 8.09 | high | | ibm-granite/granite-speech-4.1-2b | 5.33 | 8.09 | 8.37 | 9.8 | 1.33 | 2.5 | 3.78 | 3.07 | 5.7 | | |
| WER VoxPopuli | speech-asr | 5.7 | high | | ibm-granite/granite-speech-4.1-2b | 5.33 | 8.09 | 8.37 | 9.8 | 1.33 | 2.5 | 3.78 | 3.07 | 5.7 | | |
| WER | speech-asr | 5.33 | high | | ibm-granite/granite-speech-4.1-2b | 5.33 | 8.09 | 8.37 | 9.8 | 1.33 | 2.5 | 3.78 | 3.07 | 5.7 | | |
| WER SPGISpeech | speech-asr | 3.78 | high | | ibm-granite/granite-speech-4.1-2b | 5.33 | 8.09 | 8.37 | 9.8 | 1.33 | 2.5 | 3.78 | 3.07 | 5.7 | | |
| WER TED-LIUM | speech-asr | 3.07 | high | | ibm-granite/granite-speech-4.1-2b | 5.33 | 8.09 | 8.37 | 9.8 | 1.33 | 2.5 | 3.78 | 3.07 | 5.7 | |
none scraped.