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 (250 steps) - Jarrett Er
results: []
Whisper Small NSC part 1,2,3 (250 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: 0.4370
- Wer: 19.2614
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 25
- training_steps: 250
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8608 | 0.2016 | 50 | 0.6679 | 106.7614 |
| 0.5642 | 0.4032 | 100 | 0.5874 | 23.4943 |
| 0.5031 | 0.6048 | 150 | 0.5071 | 20.8239 |
| 0.4762 | 0.8065 | 200 | 0.4702 | 20.2841 |
| 0.4365 | 1.0081 | 250 | 0.4370 | 19.2614 |
Framework versions
- PEFT 0.14.0
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.1.dev0
- Tokenizers 0.20.3