<!-- 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. -->
84rry-xls-r-300M-AR
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:
- Loss: 1.0647
- Wer: 0.5078
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1428 | 9.01 | 1000 | 0.9233 | 0.7477 |
| 0.4941 | 18.02 | 2000 | 0.7661 | 0.5633 |
| 0.3609 | 27.03 | 3000 | 0.8757 | 0.5480 |
| 0.2395 | 36.04 | 4000 | 1.0097 | 0.5275 |
| 0.1671 | 45.04 | 5000 | 1.0647 | 0.5078 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
