---
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- language-and-voice-lab/samromur_children
metrics:
- wer
model-index:
- name: Whisper tiny Icelandic Children
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: language-and-voice-lab/samromur_children
      type: language-and-voice-lab/samromur_children
      config: samromur_children
      split: validation
      args: samromur_children
    metrics:
    - name: Wer
      type: wer
      value: 45.29159303206261
---

<!-- 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 tiny Icelandic Children

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the language-and-voice-lab/samromur_children dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6313
- Wer: 45.2916

## 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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 1.4343        | 0.25  | 250  | 1.4900          | 77.9349 |
| 0.7722        | 0.5   | 500  | 0.8731          | 60.2878 |
| 0.7181        | 0.75  | 750  | 0.6534          | 46.5034 |
| 0.5733        | 1.0   | 1000 | 0.6313          | 45.2916 |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.10.0
- Tokenizers 0.13.2