---
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: 0.1802
- Wer: 6.9921

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.4228        | 0.38  | 30   | 0.2223          | 8.7717 |
| 0.1719        | 0.75  | 60   | 0.1884          | 7.3780 |
| 0.1354        | 1.12  | 90   | 0.1769          | 7.1890 |
| 0.0727        | 1.5   | 120  | 0.1763          | 7.5591 |
| 0.0779        | 1.88  | 150  | 0.1691          | 6.5512 |
| 0.0468        | 2.25  | 180  | 0.1698          | 6.7244 |
| 0.0316        | 2.62  | 210  | 0.1678          | 6.3386 |
| 0.0316        | 3.0   | 240  | 0.1663          | 6.4488 |
| 0.0151        | 3.38  | 270  | 0.1770          | 8.3307 |
| 0.0143        | 3.75  | 300  | 0.1724          | 9.1024 |
| 0.0119        | 4.12  | 330  | 0.1743          | 6.9528 |
| 0.0072        | 4.5   | 360  | 0.1788          | 6.9134 |
| 0.0069        | 4.88  | 390  | 0.1802          | 6.9921 |


### Framework versions

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