C_ASR_MID / README.md
fruk19's picture
End of training
3fbf29e verified
metadata
language:
  - th
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - fruk19/C_SMALL
metrics:
  - wer
model-index:
  - name: South_asri
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: aicookcook
          type: fruk19/C_SMALL
          config: default
          split: None
          args: 'config: th'
        metrics:
          - name: Wer
            type: wer
            value: 3.7677461386031106

South_asri

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

  • Loss: 0.0347
  • Wer: 3.7677

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: 4
  • eval_batch_size: 4
  • 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: 6
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0304 2.0 6000 0.0440 5.5648
0.0061 4.0 12000 0.0358 4.1532
0.0007 6.0 18000 0.0347 3.7677

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.20.0
  • Tokenizers 0.19.1