metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
model-index:
- name: repo_name
results: []
repo_name
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.0078
- Cer: 64.3040
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0009 | 1000.0 | 1000 | 3.6991 | 71.6482 |
| 0.0004 | 2000.0 | 2000 | 3.8435 | 62.8523 |
| 0.0002 | 3000.0 | 3000 | 3.9724 | 68.7447 |
| 0.0001 | 4000.0 | 4000 | 4.0078 | 64.3040 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0