---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base-v4
  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-v4

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: 1.1814
- Wer: 43.8709

## 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: 0.0002
- train_batch_size: 16
- 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: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.4275        | 10.0  | 500  | 0.8866          | 50.2836 |
| 0.069         | 20.0  | 1000 | 1.0774          | 47.0699 |
| 0.0134        | 30.0  | 1500 | 1.1680          | 44.5689 |
| 0.002         | 40.0  | 2000 | 1.1814          | 43.8709 |


### Framework versions

- Transformers 4.45.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1