whisper-small-ar_21_02_Suite
This model is a fine-tuned version of openai/whisper-small on common voice 11 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2383
- Wer: 19.6213
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 9000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2646 | 0.39 | 1000 | 0.2858 | 25.7695 |
| 0.2052 | 0.78 | 2000 | 0.2467 | 22.6620 |
| 0.136 | 1.17 | 3000 | 0.2326 | 21.2877 |
| 0.1403 | 1.57 | 4000 | 0.2396 | 21.6093 |
| 0.1195 | 1.96 | 5000 | 0.2287 | 20.3640 |
| 0.0735 | 2.35 | 6000 | 0.2310 | 20.5386 |
| 0.0738 | 2.74 | 7000 | 0.2351 | 20.4341 |
| 0.0564 | 3.13 | 8000 | 0.2369 | 19.6703 |
| 0.0528 | 3.52 | 9000 | 0.2383 | 19.6213 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.12.0
- Datasets 2.1.0
- Tokenizers 0.12.1