metadata
language:
- ar
license: apache-2.0
base_model: openai/whisper-small
tags:
- ar_text_converter
- generated_from_trainer
datasets:
- openai/whisper-small
model-index:
- name: whisper Small Ar - mvymodel
results: []
whisper Small Ar - mvymodel
This model is a fine-tuned version of openai/whisper-small on the Our Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0742
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: 2
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0638 | 1.0 | 2494 | 0.0655 |
| 0.0524 | 2.0 | 4988 | 0.0584 |
| 0.0373 | 3.0 | 7482 | 0.0564 |
| 0.0287 | 4.0 | 9976 | 0.0600 |
| 0.0136 | 5.0 | 12470 | 0.0646 |
| 0.0069 | 6.0 | 14964 | 0.0674 |
| 0.0031 | 7.0 | 17458 | 0.0700 |
| 0.0013 | 8.0 | 19952 | 0.0723 |
| 0.0005 | 9.0 | 22446 | 0.0736 |
| 0.0002 | 10.0 | 24940 | 0.0742 |
Framework versions
- Transformers 4.32.0
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2