---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: model_whisper_base_atco2
  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. -->

# model_whisper_base_atco2

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1121
- Wer: 4.5085

## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.221         | 1.0   | 1012  | 0.1050          | 6.2112 |
| 0.062         | 2.0   | 2024  | 0.0924          | 7.5700 |
| 0.0283        | 3.0   | 3036  | 0.0885          | 5.2969 |
| 0.0152        | 4.0   | 4048  | 0.0924          | 4.7559 |
| 0.0081        | 5.0   | 5060  | 0.0966          | 5.3263 |
| 0.0058        | 6.0   | 6072  | 0.0990          | 4.5169 |
| 0.0053        | 7.0   | 7084  | 0.1019          | 4.4791 |
| 0.0041        | 8.0   | 8096  | 0.1057          | 4.2610 |
| 0.0043        | 9.0   | 9108  | 0.1058          | 4.6217 |
| 0.0031        | 10.0  | 10120 | 0.1121          | 4.5085 |


### Framework versions

- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1