metadata
license: apache-2.0
base_model: openai/whisper-tiny.en
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: veract-11-biov3.en
results: []
veract-11-biov3.en
This model is a fine-tuned version of openai/whisper-tiny.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9405
- Wer: 42.8571
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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0868 | 100.0 | 100 | 2.2346 | 42.8571 |
| 0.0129 | 200.0 | 200 | 1.9939 | 42.8571 |
| 0.0039 | 300.0 | 300 | 1.9587 | 42.8571 |
| 0.0023 | 400.0 | 400 | 1.9445 | 42.8571 |
| 0.0019 | 500.0 | 500 | 1.9405 | 42.8571 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0