---
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper_checkpoints3
  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_checkpoints3

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3786
- Wer: 0.7295

## 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: 24
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.1851        | 3.16  | 1000 | 0.2392          | 0.7080 |
| 0.0939        | 6.33  | 2000 | 0.2726          | 0.7223 |
| 0.0393        | 9.49  | 3000 | 0.3366          | 0.9990 |
| 0.0086        | 12.66 | 4000 | 0.3786          | 0.7295 |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.15.2