---
language:
- en
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper small v5-en finetuned
  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 v5-en finetuned

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the my_audio_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1560
- Wer: 5.6915

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- training_steps: 3000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 0.1138        | 5.8309  | 1000 | 0.1326          | 6.3035 |
| 0.004         | 11.6618 | 2000 | 0.1507          | 5.7015 |
| 0.0014        | 17.4927 | 3000 | 0.1560          | 5.6915 |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1