<!-- 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. -->
tamasheq-99-2.feature_ext
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-arabic on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9535
- Wer: 0.9815
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.2797 | 15.79 | 300 | 2.8964 | 1.0 |
| 2.9763 | 31.58 | 600 | 2.7486 | 1.0 |
| 2.011 | 47.37 | 900 | 1.5549 | 0.9778 |
| 0.8448 | 63.16 | 1200 | 1.6495 | 0.9852 |
| 0.6122 | 78.95 | 1500 | 1.7794 | 0.9852 |
| 0.5039 | 94.74 | 1800 | 1.9535 | 0.9815 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
