This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.6073 | 2.1 | 250 | 3.5111 | 1.0 |
| 3.0828 | 4.2 | 500 | 3.5133 | 1.0 |
| 1.9969 | 6.3 | 750 | 1.3924 | 0.9577 |
| 0.9279 | 8.4 | 1000 | 0.8378 | 0.7243 |
| 0.6692 | 10.5 | 1250 | 0.7367 | 0.6394 |
| 0.5273 | 12.6 | 1500 | 0.6703 | 0.5907 |
| 0.4314 | 14.7 | 1750 | 0.6594 | 0.5718 |
| 0.3809 | 16.8 | 2000 | 0.6138 | 0.5559 |
| 0.3934 | 18.9 | 2250 | 0.6357 | 0.5496 |
pytorch_model.bin 1.3 GBtraining_args.bin 3.1 kB