metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Model
results: []
Model
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3208
- Wer: 0.2936
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 240
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1346 | 0.43 | 100 | 0.8999 | 196.8440 |
| 0.4533 | 0.85 | 200 | 0.3208 | 0.2936 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1