metadata

license: apache-2.0
base_model: NbAiLab/nb-whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - samromur_asr
metrics:
  - wer
model-index:
  - name: whisper-tiny-no-is
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: samromur_asr
          type: samromur_asr
          config: samromur_asr
          split: test
          args: samromur_asr
        metrics:
          - name: Wer
            type: wer
            value: 76.29381905046283

whisper-tiny-no-is

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

Loss: 1.6028
Wer: 76.2938

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: 100
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.809	0.0889	500	1.8714	81.6100
1.5205	0.1778	1000	1.6028	76.2938

Framework versions

Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1