---
language:
- fy
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Western Frisian (Netherlands)
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: mozilla-foundation/common_voice_11_0 fy-NL
      type: mozilla-foundation/common_voice_11_0
      config: fy-NL
      split: test
      args: fy-NL
    metrics:
    - name: Wer
      type: wer
      value: 25.76645465589938
---

# Whisper Small Western Frisian (Netherlands)

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_11_0 fy-NL dataset.
This is an attempt for cross lingual transfer from English to Frisian, since Whisper doesn't support Frisian.

It achieves the following results on the evaluation set:
- Loss: 0.6915
- Wer: 25.7665

## 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: 64
- eval_batch_size: 32
- 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: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.004         | 17.0  | 1000 | 0.6402          | 26.9349 |
| 0.0006        | 34.01 | 2000 | 0.6915          | 25.7665 |
| 0.0003        | 51.01 | 3000 | 0.7274          | 25.7736 |
| 0.0002        | 68.01 | 4000 | 0.7456          | 25.8772 |
| 0.0002        | 86.0  | 5000 | 0.7580          | 25.9272 |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2