Automatic Speech Recognition on Multilingual ASR Corpus Czech (test)
5.7CERH-Softmax (Huffman)
Evaluation results
| Method | Links | |
|---|---|---|
| H-Softmax (Huffman)Training=All, Softmax Type=Huffman2025.01 | 5.7 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-base, Distance Metric=2-med S-Euc2025.01 | 5.7 | |
| SoftmaxTraining=All, Softmax Type=Standard Softmax2025.01 | 6 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-large, Distance Metric=2-med S-Euc2025.01 | 6 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-XL, Distance Metric=Wtd Corr2025.01 | 6.5 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=LABSE, Distance Metric=Median Euc2025.01 | 6.5 | |
| embedding-based H-SoftmaxTraining=All, Strategy=Mono-Map, Weighting=Avg CB2025.01 | 6.7 |