metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-ali-eng
results: []
whisper-ali-eng
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: 0.2831
- Wer: 9.4918
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 25
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1598 | 1.0 | 4985 | 0.2136 | 10.7623 |
| 0.0673 | 2.0 | 9970 | 0.2173 | 11.1360 |
| 0.016 | 3.0 | 14955 | 0.2466 | 10.7623 |
| 0.0114 | 4.0 | 19940 | 0.2658 | 9.7907 |
| 0.0005 | 5.0 | 24925 | 0.2831 | 9.4918 |
Framework versions
- Transformers 4.53.0
- Pytorch 2.4.1+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2