---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: ap-jLype7eJniXiXbhFmRXQx3
  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. -->

# ap-jLype7eJniXiXbhFmRXQx3

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4775
- Model Preparation Time: 0.0215
- Wer: 0.1259

## 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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time | Wer    |
|:-------------:|:------:|:----:|:---------------:|:----------------------:|:------:|
| 0.4643        | 0.9791 | 41   | 0.4187          | 0.0215                 | 0.1415 |
| 0.2421        | 1.9791 | 82   | 0.3216          | 0.0215                 | 0.1133 |
| 0.1917        | 2.9791 | 123  | 0.3110          | 0.0215                 | 0.1113 |
| 0.1372        | 3.9791 | 164  | 0.3263          | 0.0215                 | 0.1222 |
| 0.0873        | 4.9791 | 205  | 0.3568          | 0.0215                 | 0.1108 |
| 0.0598        | 5.9791 | 246  | 0.3809          | 0.0215                 | 0.1172 |
| 0.0323        | 6.9791 | 287  | 0.4263          | 0.0215                 | 0.1150 |
| 0.0284        | 7.9791 | 328  | 0.4463          | 0.0215                 | 0.1448 |
| 0.0149        | 8.9791 | 369  | 0.4452          | 0.0215                 | 0.1219 |
| 0.0131        | 9.9791 | 410  | 0.4775          | 0.0215                 | 0.1259 |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0