---
language:
- no
license: apache-2.0
tags:
- whisper-event
- norwegian
datasets:
- NbAiLab/NCC_S
- NbAiLab/NPSC
- NbAiLab/NST
- google/fleurs
metrics:
- wer
model-index:
- name: Whisper Tiny Norwegian Bokmål
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: FLEURS
      type: google/fleurs
      config: nb_no
      split: test
      args: nb_no
    metrics:
    - name: Wer
      type: wer
      value: 47.08
---

# Whisper Tiny Norwegian Bokmål

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) trained on several datasets.

It is currently in the middle of a large trainingi. Currently achieves the following results on the evaluation set:
- Loss: 1.464
- Wer: 47.08

## Model description

The model is trained on a large corpus of roughly 5.000 hours of voice. The sources are subtitles from the Norwegian broadcaster NRK, transcribed speeches from the Norwegian parliament and voice recordings from Norsk Språkteknologi. 

## Intended uses & limitations

The model will be free for everyone to use when it is finished.

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 3e-06
- train_batch_size: 128
- 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: 100.000 (currently 4.000)
- mixed_precision_training: fp16

### Training results
See [Tensorboad Metrics](https://huggingface.co/NbAiLab/whisper-tiny-nob/tensorboard)