whisper-medium-tamil-2
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1695
- Wer: 77.1245
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0174 | 1.14 | 100 | 1.0930 | 78.3945 |
| 0.0184 | 2.29 | 200 | 1.1317 | 76.6855 |
| 0.0103 | 3.43 | 300 | 1.1273 | 76.6541 |
| 0.0039 | 4.57 | 400 | 1.1638 | 76.7952 |
| 0.0014 | 5.71 | 500 | 1.1695 | 77.1245 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1
- Downloads last month
- 23
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.