Edit model card

Whisper Small Italian

This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1185
  • Wer: 17.3916

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: 16
  • eval_batch_size: 8
  • gradient_accumulation_steps: 1
  • 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: 500
  • training_steps: 954

Training results

Training Loss Step Validation Loss Wer
1.4744 100 1.1852 117.6059
0.7241 200 0.7452 79.7386
0.3321 300 0.3215 21.0497
0.2930 400 0.3030 20.2129
0.2698 500 0.2982 19.7635
0.2453 600 0.2898 19.0097
0.2338 700 0.2768 18.7054
0.2402 800 0.2646 18.2214
0.2340 900 0.2581 17.3916

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.1
  • Tokenizers 0.13.2
Downloads last month
20
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train whispy/whisper_italian

Spaces using whispy/whisper_italian 5

Evaluation results