Edit model card

Whisper base ID - Augmented

This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_12_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2277
  • Wer: 11.2027

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: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • training_steps: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.5509 0.77 200 0.3243 13.8588
0.3844 1.54 400 0.2590 11.1782
0.259 2.31 600 0.2422 18.6813
0.1608 3.07 800 0.2361 11.6678
0.1205 3.84 1000 0.2277 11.2027

Framework versions

  • Transformers 4.29.0.dev0
  • Pytorch 2.0.0+cu117
  • Datasets 2.10.1
  • Tokenizers 0.13.2
Downloads last month
0

Dataset used to train TheRains/output-base-id

Evaluation results