---
language:
- en
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: openai/whisper-base
  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. -->

# openai/whisper-base

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the pphuc25/EngMed dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1666
- Wer: 60.2158

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer     |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
| 1.1826        | 1.0   | 2506  | 1.7835          | 68.6355 |
| 0.7887        | 2.0   | 5012  | 1.8341          | 59.1793 |
| 0.4831        | 3.0   | 7518  | 2.0149          | 61.7493 |
| 0.3118        | 4.0   | 10024 | 2.2028          | 61.6546 |
| 0.1658        | 5.0   | 12530 | 2.4079          | 61.1198 |
| 0.1132        | 6.0   | 15036 | 2.5319          | 62.6390 |
| 0.0881        | 7.0   | 17542 | 2.6463          | 60.3815 |
| 0.0576        | 8.0   | 20048 | 2.7534          | 62.1799 |
| 0.0475        | 9.0   | 22554 | 2.8226          | 59.7141 |
| 0.0255        | 10.0  | 25060 | 2.9442          | 61.1482 |
| 0.0195        | 11.0  | 27566 | 2.9715          | 60.5282 |
| 0.0192        | 12.0  | 30072 | 2.9949          | 61.1103 |
| 0.006         | 13.0  | 32578 | 3.0603          | 59.3639 |
| 0.0164        | 14.0  | 35084 | 3.0546          | 59.6479 |
| 0.0024        | 15.0  | 37590 | 3.0842          | 60.2111 |
| 0.004         | 16.0  | 40096 | 3.0938          | 60.4051 |
| 0.0112        | 17.0  | 42602 | 3.1210          | 60.3862 |
| 0.003         | 18.0  | 45108 | 3.1520          | 59.1935 |
| 0.0017        | 19.0  | 47614 | 3.1416          | 60.1685 |
| 0.0           | 20.0  | 50120 | 3.1666          | 60.2158 |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1