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 |
|---|---|---|---|---|
| 3.4351 | 4.0 | 500 | 1.2740 | 0.8259 |
| 0.5828 | 8.0 | 1000 | 0.4276 | 0.4403 |
| 0.2274 | 12.0 | 1500 | 0.4646 | 0.3739 |
| 0.135 | 16.0 | 2000 | 0.4320 | 0.3662 |
| 0.0962 | 20.0 | 2500 | 0.4831 | 0.3607 |
| 0.0719 | 24.0 | 3000 | 0.4506 | 0.3463 |
| 0.0556 | 28.0 | 3500 | 0.4519 | 0.3375 |
pytorch_model.bin 378 MBtraining_args.bin 2.9 kB