Automatic Speech Recognition on Multilingual ASR Corpus Russian ru (test)
8.3CERembedding-based H-Softmax
Evaluation Results
| Method | Links | |
|---|---|---|
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-base, Distance Metric=2-med S-Euc2025.01 | 8.3 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-XL, Distance Metric=Wtd Corr2025.01 | 8.4 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=XLM-large, Distance Metric=2-med S-Euc2025.01 | 8.5 | |
| embedding-based H-SoftmaxTraining=All, Strategy=Mono-Map, Weighting=Avg CB2025.01 | 8.6 | |
| H-Softmax (Huffman)Training=All, Softmax Type=Huffman2025.01 | 8.9 | |
| SoftmaxTraining=All, Softmax Type=Standard Softmax2025.01 | 9.8 | |
| embedding-based H-SoftmaxTraining=All, Embedding Model=LABSE, Distance Metric=Median Euc2025.01 | 10.3 |