metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - ravnursson_asr
metrics:
  - wer
model-index:
  - name: whisper-tiny-fo
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ravnursson_asr
          type: ravnursson_asr
          config: ravnursson_asr
          split: None
          args: ravnursson_asr
        metrics:
          - name: Wer
            type: wer
            value: 97.39999999999999

whisper-tiny-fo

This model is a fine-tuned version of openai/whisper-tiny on the ravnursson_asr dataset. It achieves the following results on the evaluation set:

Loss: 2.3908
Wer: 97.4000

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: 5
training_steps: 40
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.43	10	3.7140	118.4000
No log	2.86	20	2.6041	100.2
2.8026	4.29	30	2.4362	97.6
2.8026	5.71	40	2.3908	97.4000

Framework versions

Transformers 4.38.2
Pytorch 2.2.1
Datasets 2.18.0
Tokenizers 0.15.1