---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: ap-vIPVV9dqluiiO2kf7JwA61
  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-vIPVV9dqluiiO2kf7JwA61

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: 0.3485
- Model Preparation Time: 0.0151
- Wer: 0.1102

## 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-06
- 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    |
|:-------------:|:------:|:----:|:---------------:|:----------------------:|:------:|
| 0.742         | 0.9791 | 41   | 0.7811          | 0.0151                 | 0.1875 |
| 0.5242        | 1.9791 | 82   | 0.5559          | 0.0151                 | 0.1543 |
| 0.328         | 2.9791 | 123  | 0.3325          | 0.0151                 | 0.1214 |
| 0.2466        | 3.9791 | 164  | 0.2946          | 0.0151                 | 0.1120 |
| 0.2118        | 4.9791 | 205  | 0.2802          | 0.0151                 | 0.1094 |
| 0.1682        | 5.9791 | 246  | 0.2751          | 0.0151                 | 0.1052 |
| 0.1316        | 6.9791 | 287  | 0.2780          | 0.0151                 | 0.1070 |
| 0.0857        | 7.9791 | 328  | 0.3017          | 0.0151                 | 0.1058 |
| 0.0725        | 8.9791 | 369  | 0.3152          | 0.0151                 | 0.1060 |
| 0.0448        | 9.9791 | 410  | 0.3485          | 0.0151                 | 0.1102 |


### Framework versions

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