whisper-tiny-ar
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8394
- Wer: 86.0500
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: 128
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0265 | 1.0 | 122 | 1.0110 | 98.4608 |
| 0.9208 | 2.0 | 244 | 0.9148 | 88.3812 |
| 0.8169 | 3.0 | 366 | 0.8394 | 86.0500 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 33
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.