metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base.en
results: []
whisper-base.en
This model is a fine-tuned version of openai/whisper-base.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0027
- Wer: 2.0414
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: 3500
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.3217 | 1.62 | 500 | 0.2442 | 10.2872 |
0.0874 | 3.25 | 1000 | 0.0774 | 5.5339 |
0.0459 | 4.87 | 1500 | 0.0268 | 3.3624 |
0.012 | 6.49 | 2000 | 0.0094 | 2.7119 |
0.0041 | 8.12 | 2500 | 0.0041 | 2.1115 |
0.0035 | 9.74 | 3000 | 0.0030 | 2.1315 |
0.0036 | 11.36 | 3500 | 0.0027 | 2.0414 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2