| named-entity-recognition-on-slue | W2V2-L-LL60K (pipeline approach, uses LM) | #1 | F1 (%): 69.6label-F1 (%): 82.2Text model: DeBERTa-L |
| named-entity-recognition-on-slue | W2V2-B-LS960 (pipeline approach, uses LM) | #2 | F1 (%): 68.0label-F1 (%): 79.8Text model: DeBERTa-L |
| named-entity-recognition-on-slue | W2V2-L-LL60K (e2e approach, uses LM) | #4 | F1 (%): 64.8label-F1 (%): 73.3Text model: N/A |
| named-entity-recognition-on-slue | W2V2-B-LS960 (e2e approach, uses LM) | #5 | F1 (%): 63.4label-F1 (%): 71.7Text model: N/A |
| named-entity-recognition-on-slue | HuBERT-B-LS960 (e2e approach, uses LM) | #6 | F1 (%): 61.9label-F1 (%): 70.3Text model: N/A |
| named-entity-recognition-on-slue | W2V2-B-VP100K (e2e approach, uses LM) | #7 | F1 (%): 61.8label-F1 (%): 69.8Text model: N/A |
| named-entity-recognition-on-slue | W2V2-L-LL60K (pipeline approach) | #8 | F1 (%): 57.8label-F1 (%): 78.8Text model: DeBERTa-L |
| named-entity-recognition-on-slue | W2V2-L-LL60K (e2e approach) | #9 | F1 (%): 50.9label-F1 (%): 64.7 |
| named-entity-recognition-on-slue | W2V2-B-LS960 (e2e approach) | #10 | F1 (%): 50.2label-F1 (%): 64.0 |
| named-entity-recognition-on-slue | HuBERT-B-LS960 (e2e approach) | #11 | F1 (%): 49.8label-F1 (%): 62.9 |
| named-entity-recognition-on-slue | W2V2-B-LS960 (pipeline approach) | #12 | F1 (%): 49.5label-F1 (%): 74.2Text model: DeBERTa-L |
| named-entity-recognition-on-slue | W2V2-B-VP100K (e2e approach) | #13 | F1 (%): 47.9label-F1 (%): 60.8 |
| sentiment-analysis-on-slue | W2V2-L-LL60K (pipeline approach, uses LM) | #1 | Recall (%): 60.4F1 (%): 63.3Text model: DeBERTa-L |
| sentiment-analysis-on-slue | W2V2-L-LL60K (pipeline approach) | #2 | Recall (%): 60.2F1 (%): 63.3Text model: DeBERTa-L |
| sentiment-analysis-on-slue | W2V2-B-LS960 (pipeline approach, uses LM) | #3 | Recall (%): 60.0F1 (%): 62.9Text model: DeBERTa-L |
| sentiment-analysis-on-slue | W2V2-B-LS960 (pipeline approach) | #4 | Recall (%): 59.0F1 (%): 61.8Text model: DeBERTa-L |
| sentiment-analysis-on-slue | W2V2-L-LL60K (e2e approach) | #5 | Recall (%): 49.2F1 (%): 48.5Text model: N/A |
| sentiment-analysis-on-slue | HuBERT-B-LS960 (e2e approach) | #6 | Recall (%): 47.5F1 (%): 48.0Text model: N/A |
| sentiment-analysis-on-slue | W2V2-B-LS960 (e2e approach) | #7 | Recall (%): 46.0F1 (%): 46.6Text model: N/A |
| sentiment-analysis-on-slue | W2V2-B-VP100K (e2e approach) | #8 | Recall (%): 38.7F1 (%): 38.4Text model: N/A |
| speech-recognition-on-slue | W2V2-L-LL60K (+ TED-LIUM 3 LM) | #1 | VoxPopuli (Dev): 9.1VoxPopuli (Test): 9.3VoxCeleb (Dev): 9.1… |
| speech-recognition-on-slue | W2V2-B-LS960 (+ TED-LIUM 3 LM) | #2 | VoxPopuli (Dev): 12.0VoxPopuli (Test): 12.2VoxCeleb (Dev): 13.2… |
| speech-recognition-on-slue | W2V2-L-LL60K (+ in-domain LM) | #3 | VoxPopuli (Dev): 12.0VoxPopuli (Test): 12.5VoxCeleb (Dev): 11.8… |
| speech-recognition-on-slue | W2V2-L-LL60K | #4 | VoxPopuli (Dev): 14.0VoxPopuli (Test): 12.1VoxCeleb (Dev): 11.0… |
| speech-recognition-on-slue | W2V2-B-LS960 (+ in-domain LM) | #5 | VoxPopuli (Dev): 14.6VoxPopuli (Test): 15.2VoxCeleb (Dev): 15.2… |
| speech-recognition-on-slue | W2V2-B-LS960 | #6 | VoxPopuli (Dev): 17.2VoxPopuli (Test): 17.9VoxCeleb (Dev): 17.2… |
| speech-recognition-on-slue | HuBERT-B-LS960 | #7 | VoxPopuli (Dev): 18.6VoxPopuli (Test): 19.1VoxCeleb (Dev): 19.6… |
| speech-recognition-on-slue | W2V2-B-VP100K | #8 | VoxPopuli (Dev): 21.6VoxPopuli (Test): 22.4VoxCeleb (Dev): 29.9… |