---
language:
- sv
license: apache-2.0
tags:
- i-dont-know-what-im-doing
- generated_from_trainer
datasets:
- fimster/NST_small_whisper
metrics:
- wer
model-index:
- name: Whisper Small sv-SE NST - Lab 2
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: NST Swedish ASR
      type: fimster/NST_small_whisper
      config: speech
      split: None
      args: 'config: speech, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 10.167794316644112
---

<!-- 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 Small sv-SE NST - Lab 2

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the NST Swedish ASR dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1305
- Wer: 10.1678

## 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: 1e-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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.1635        | 0.67  | 1000 | 0.1694          | 13.4993 |
| 0.07          | 1.33  | 2000 | 0.1431          | 11.3802 |
| 0.0597        | 2.0   | 3000 | 0.1302          | 10.4682 |
| 0.0193        | 2.67  | 4000 | 0.1305          | 10.1678 |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2