metadata
library_name: peft
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper small NSC part 1,2,3 (500 steps) - Jarrett Er
results: []
Whisper small NSC part 1,2,3 (500 steps) - Jarrett Er
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2905
- Wer: 48.0
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 1
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.0118 | 9.01 | 50 | 1.7796 | 352.0 |
| 0.2479 | 19.01 | 100 | 0.3092 | 56.0000 |
| 0.0047 | 29.01 | 150 | 0.2667 | 54.0 |
| 0.0005 | 39.01 | 200 | 0.2630 | 44.0 |
| 0.0002 | 49.01 | 250 | 0.2685 | 50.0 |
| 0.0001 | 59.01 | 300 | 0.2749 | 50.0 |
| 0.0001 | 69.01 | 350 | 0.2836 | 50.0 |
| 0.0001 | 79.01 | 400 | 0.2892 | 50.0 |
| 0.0001 | 89.01 | 450 | 0.2894 | 48.0 |
| 0.0001 | 99.01 | 500 | 0.2905 | 48.0 |
Framework versions
- PEFT 0.14.0
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.1.dev0
- Tokenizers 0.20.3