idaracecilia's picture
End of training
cb9f0e6 verified
|
raw
history blame
2.1 kB
metadata
language:
  - eng
license: apache-2.0
base_model: openai/whisper-base.en
tags:
  - generated_from_trainer
datasets:
  - fyp
metrics:
  - wer
model-index:
  - name: Whisper Fine tuned Base
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Fyp Dataset
          type: fyp
          args: 'config: eng, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 15.01856226797165

Whisper Fine tuned Base

This model is a fine-tuned version of openai/whisper-base.en on the Fyp Dataset dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3550
  • Wer: 15.0186

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 5
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.3123 0.5 25 0.4652 20.1147
0.3282 1.0 50 0.3655 16.2673
0.0376 1.5 75 0.3693 15.4573
0.0468 2.0 100 0.3754 20.2497
0.0067 2.5 125 0.3585 15.3898
0.0098 3.0 150 0.3550 15.0186

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1