This model is a fine-tuned version of facebook/wav2vec2-large-lv60 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 |
|---|---|---|---|---|
| 5.3773 | 33.33 | 500 | 2.9693 | 1.0 |
| 1.4746 | 66.67 | 1000 | 0.5050 | 0.3359 |
| 0.1067 | 100.0 | 1500 | 0.5981 | 0.3054 |
| 0.0388 | 133.33 | 2000 | 0.6192 | 0.2712 |
| 0.0244 | 166.67 | 2500 | 0.6392 | 0.2776 |
| 0.018 | 200.0 | 3000 | 0.6615 | 0.2788 |
pytorch_model.bin 1.3 GBtraining_args.bin 2.9 kB