Whisper Base Ur - TahaMan
This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1893
- Wer: 60.7652
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1544 | 4.0 | 50 | 0.9766 | 57.2633 |
| 0.5159 | 8.0 | 100 | 0.9178 | 75.0324 |
| 0.2399 | 12.0 | 150 | 0.9604 | 76.7185 |
| 0.1005 | 16.0 | 200 | 1.0300 | 59.1440 |
| 0.0372 | 20.0 | 250 | 1.0988 | 70.0389 |
| 0.0168 | 24.0 | 300 | 1.1373 | 66.3424 |
| 0.0109 | 28.0 | 350 | 1.1638 | 61.0246 |
| 0.0085 | 32.0 | 400 | 1.1781 | 61.0895 |
| 0.0074 | 36.0 | 450 | 1.1864 | 60.9598 |
| 0.0069 | 40.0 | 500 | 1.1893 | 60.7652 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.