metadata
license: apache-2.0
base_model: openai/whisper-large
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: output_large
results: []
output_large
This model is a fine-tuned version of openai/whisper-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6419
- Wer: 25.1240
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: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.45 | 10 | 0.8644 | 49.3460 |
| No log | 0.91 | 20 | 0.7146 | 28.9581 |
| 0.8368 | 1.36 | 30 | 0.6654 | 25.4849 |
| 0.8368 | 1.82 | 40 | 0.6558 | 25.2143 |
| 0.3123 | 2.27 | 50 | 0.6419 | 25.1240 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2