<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xls-r-300m-nya
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8146
- Wer: 0.5774
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.7787 | 0.49 | 500 | 0.9349 | 0.6845 |
0.3388 | 0.99 | 1000 | 0.6850 | 0.5170 |
0.226 | 1.48 | 1500 | 0.5704 | 0.4120 |
0.2019 | 1.97 | 2000 | 0.5366 | 0.3883 |
0.1536 | 2.46 | 2500 | 0.5044 | 0.3591 |
0.1367 | 2.96 | 3000 | 0.4721 | 0.3308 |
0.1091 | 3.45 | 3500 | 0.4947 | 0.3338 |
0.2757 | 3.94 | 4000 | 0.7905 | 0.5486 |
0.3992 | 4.43 | 4500 | 0.8146 | 0.5774 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2