Aviral2412's picture
End of training
396e8e8 verified
metadata
base_model: Aviral2412/mini_model
tags:
  - generated_from_trainer
datasets:
  - common_voice_1_0
metrics:
  - wer
model-index:
  - name: fineturning-with-pretraining-3
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_1_0
          type: common_voice_1_0
          config: en
          split: validation
          args: en
        metrics:
          - name: Wer
            type: wer
            value: 1.0000323289796973

fineturning-with-pretraining-3

This model is a fine-tuned version of Aviral2412/mini_model on the common_voice_1_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 2.9160
  • Wer: 1.0000

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: 32
  • 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: 1000
  • num_epochs: 30
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
6.0042 4.27 500 3.1928 1.0000
2.9673 8.55 1000 3.0856 1.0000
2.9929 12.82 1500 3.0173 1.0000
2.9458 17.09 2000 2.9282 1.0000
2.9084 21.37 2500 2.9734 1.0000
2.8651 25.64 3000 2.9234 1.0000
2.8307 29.91 3500 2.9160 1.0000

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2