metadata
license: mit
base_model: distil-whisper/distil-large-v2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: rao-vandromme-purcell-distil-finetuned
results: []
rao-vandromme-purcell-distil-finetuned
This model is a fine-tuned version of distil-whisper/distil-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0590
- Wer: 2.9688
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: 5
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6205 | 0.29 | 10 | 0.2496 | 3.4375 |
| 0.073 | 0.59 | 20 | 0.0745 | 2.5 |
| 0.2899 | 0.88 | 30 | 0.0647 | 3.125 |
| 0.034 | 1.18 | 40 | 0.0674 | 3.2812 |
| 0.0507 | 1.47 | 50 | 0.0590 | 2.9688 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0