Automatic Speech Recognition on Multilingual ASR Corpus Bashkir (test)
10.6CERembedding-based H-Softmax
Evaluation results
| Method | Links | |
|---|---|---|
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-large, Distance Metric=2-med S-Euc2025.01 | 10.6 | |
| H-Softmax (Huffman)Training=All, Softmax Type=Huffman2025.01 | 10.8 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=LABSE, Distance Metric=Median Euc2025.01 | 10.9 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-XL, Distance Metric=Wtd Corr2025.01 | 11.1 | |
| embedding-based H-SoftmaxTraining=All, Strategy=Mono-Map, Weighting=Avg CB2025.01 | 12.1 | |
| SoftmaxTraining=All, Softmax Type=Standard Softmax2025.01 | 12.4 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-base, Distance Metric=2-med S-Euc2025.01 | 13.7 |