---
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 2 (500 steps) - Jarrett Er
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Whisper Small NSC part 2 (500 steps) - Jarrett Er

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0264
- Wer: 0.8543

## 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: 32
- 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: 50
- training_steps: 500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.0749        | 1.3514 | 100  | 0.1221          | 6.0701 |
| 0.034         | 2.7027 | 200  | 0.0600          | 2.3381 |
| 0.0171        | 4.0541 | 300  | 0.0346          | 1.0342 |
| 0.0097        | 5.4054 | 400  | 0.0278          | 0.9442 |
| 0.0087        | 6.7568 | 500  | 0.0264          | 0.8543 |


### Framework versions

- PEFT 0.14.0
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.1.dev0
- Tokenizers 0.20.3