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 |
|---|---|---|---|---|
| 3.5329 | 4.0 | 500 | 1.5741 | 1.0400 |
| 0.6432 | 8.0 | 1000 | 0.4571 | 0.4418 |
| 0.2214 | 12.0 | 1500 | 0.4381 | 0.3823 |
| 0.1294 | 16.0 | 2000 | 0.4706 | 0.3911 |
| 0.0868 | 20.0 | 2500 | 0.5252 | 0.3662 |
| 0.0616 | 24.0 | 3000 | 0.4828 | 0.3458 |
| 0.0461 | 28.0 | 3500 | 0.4500 | 0.3391 |
pytorch_model.bin 378 MBtraining_args.bin 2.9 kB