moonseok's picture
End of training
46921b8
metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: whisper_speechcommandsV2_final
    results: []

whisper_speechcommandsV2_final

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5364
  • Accuracy: 0.9067

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: 3e-05
  • train_batch_size: 42
  • eval_batch_size: 42
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 168
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0374 1.0 505 0.4618 0.9014
0.0307 2.0 1010 0.4482 0.9022
0.0312 3.0 1515 0.4575 0.9039
0.022 4.0 2021 0.5217 0.9014
0.0227 5.0 2526 0.4511 0.9065
0.005 6.0 3031 0.5395 0.9053
0.0016 7.0 3536 0.5289 0.9045
0.001 8.0 4042 0.5771 0.9055
0.0002 9.0 4547 0.5407 0.9065
0.0001 10.0 5050 0.5364 0.9067

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1