Automatic Speech Recognition on OpenSLR-54 (test)
16.82WERfine-tuned Wav2Vec2 XLS-R
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| fine-tuned Wav2Vec2 XLS-RModel Type=Self-supervised transformer, Fine-tuned=true2026.02 | 16.82 | 2.72 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| fine-tuned Wav2Vec2 XLS-RModel Type=Self-supervised transformer, Fine-tuned=true2026.02 | 16.82 | 2.72 |