---
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper-Small Augmented for SEP-28k
  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 Augmented for SEP-28k

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the SEP-28K dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7265
- Wer: 13.7591

## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5910
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.0229        | 5.1020  | 1000 | 0.5061          | 13.5547 |
| 0.0018        | 10.2041 | 2000 | 0.6259          | 13.6204 |
| 0.0006        | 15.3061 | 3000 | 0.6754          | 13.6496 |
| 0.0005        | 20.4082 | 4000 | 0.7105          | 13.7007 |
| 0.0004        | 25.5102 | 5000 | 0.7265          | 13.7591 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0