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

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1142
- Wer: 3.7226

## 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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.0667        | 0.3534 | 100  | 0.1267          | 4.8230 |
| 0.0693        | 0.7067 | 200  | 0.1188          | 4.1087 |
| 0.0614        | 1.0601 | 300  | 0.1133          | 3.7907 |
| 0.0274        | 1.4134 | 400  | 0.1128          | 3.7503 |
| 0.0365        | 1.7668 | 500  | 0.1113          | 3.8513 |
| 0.014         | 2.1201 | 600  | 0.1106          | 3.7201 |
| 0.0165        | 2.4735 | 700  | 0.1116          | 3.7352 |
| 0.0137        | 2.8269 | 800  | 0.1096          | 3.6999 |
| 0.007         | 3.1802 | 900  | 0.1114          | 3.6216 |
| 0.007         | 3.5336 | 1000 | 0.1130          | 3.6317 |
| 0.0077        | 3.8869 | 1100 | 0.1128          | 3.6645 |
| 0.0056        | 4.2403 | 1200 | 0.1138          | 3.7302 |
| 0.005         | 4.5936 | 1300 | 0.1142          | 3.7226 |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3