metadata
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper_checkpoints2
results: []
whisper_checkpoints2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2958
- Wer: 0.0880
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: 24
- 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 | Wer |
|---|---|---|---|---|
| 0.0051 | 0.52 | 500 | 0.2561 | 1.0 |
| 0.0074 | 1.04 | 1000 | 0.2729 | 0.1058 |
| 0.0076 | 1.56 | 1500 | 0.2769 | 0.0959 |
| 0.003 | 2.08 | 2000 | 0.2745 | 0.0954 |
| 0.0027 | 2.6 | 2500 | 0.2838 | 0.0877 |
| 0.0021 | 3.12 | 3000 | 0.2883 | 0.0880 |
| 0.0021 | 3.64 | 3500 | 0.2938 | 0.0910 |
| 0.0018 | 4.16 | 4000 | 0.2958 | 0.0880 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.15.2