README.md

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-5k-steps
    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: 51.60346372051359

whisper-tiny-no-is-5k-steps

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: 0.7830
• Wer: 51.6035

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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2696	0.1778	1000	1.3551	69.4512
0.9101	0.3556	2000	0.9833	60.0096
0.7626	0.5333	3000	0.8596	54.7590
0.7316	0.7111	4000	0.8014	52.3165
0.7269	0.8889	5000	0.7830	51.6035

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1