---
language:
- nl
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Large V2
  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 Large V2

This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1620
- Wer: 5.3772

## 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: 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: 20
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.42          | 0.38  | 30   | 0.1892          | 7.8607 |
| 0.1804        | 0.75  | 60   | 0.1588          | 7.0793 |
| 0.1293        | 1.12  | 90   | 0.1579          | 6.9632 |
| 0.075         | 1.5   | 120  | 0.1520          | 6.4371 |
| 0.0734        | 1.88  | 150  | 0.1482          | 5.9961 |
| 0.05          | 2.25  | 180  | 0.1534          | 5.6480 |
| 0.0299        | 2.62  | 210  | 0.1534          | 5.5629 |
| 0.0332        | 3.0   | 240  | 0.1480          | 5.6712 |
| 0.0157        | 3.38  | 270  | 0.1506          | 5.3694 |
| 0.0148        | 3.75  | 300  | 0.1563          | 5.3772 |
| 0.0113        | 4.12  | 330  | 0.1578          | 5.2998 |
| 0.0073        | 4.5   | 360  | 0.1633          | 5.2611 |
| 0.007         | 4.88  | 390  | 0.1620          | 5.3772 |


### Framework versions

- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0