This model is a fine-tuned version of facebook/wav2vec2-base 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 |
|---|---|---|---|---|
| 3.4323 | 4.0 | 500 | 1.3259 | 0.9859 |
| 0.5966 | 8.0 | 1000 | 0.4682 | 0.4442 |
| 0.2187 | 12.0 | 1500 | 0.4490 | 0.3875 |
| 0.1274 | 16.0 | 2000 | 0.4595 | 0.3727 |
| 0.0859 | 20.0 | 2500 | 0.4819 | 0.3683 |
| 0.0602 | 24.0 | 3000 | 0.4524 | 0.3514 |
| 0.0449 | 28.0 | 3500 | 0.4796 | 0.3434 |
pytorch_model.bin 378 MBtraining_args.bin 2.9 kB