<!-- 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. -->
whisper_small_arabic_cv11_no_diacs_2
This model is a fine-tuned version of Seyfelislem/whisper_small_arabic_cv11_no_diacs on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2440
- Wer: 20.2541
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2252 | 0.83 | 1000 | 0.2624 | 24.0662 |
| 0.111 | 1.66 | 2000 | 0.2384 | 21.8571 |
| 0.0683 | 2.5 | 3000 | 0.2429 | 20.6727 |
| 0.0378 | 3.33 | 4000 | 0.2440 | 20.2541 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2
