This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice 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 |
|---|---|---|---|---|
| 10.0237 | 0.49 | 100 | 4.2075 | 0.9792 |
| 3.313 | 0.98 | 200 | 3.0232 | 0.9792 |
| 2.9469 | 1.47 | 300 | 2.7591 | 0.9792 |
| 1.4217 | 1.96 | 400 | 0.8397 | 0.6219 |
| 0.5598 | 2.45 | 500 | 0.6085 | 0.5087 |
| 0.4507 | 2.94 | 600 | 0.4512 | 0.4317 |
| 0.2775 | 3.43 | 700 | 0.3839 | 0.3751 |
| 0.2047 | 3.92 | 800 | 0.3276 | 0.3489 |
pytorch_model.bin 1.3 GBtraining_args.bin 2.8 kB