Edit model card

Whisper Small Italian

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 it dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2517
  • Wer: 11.2714

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: 64
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 2.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2529 1.0 466 0.2758 12.4907
0.1711 2.0 932 0.2517 11.2714

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1
  • Tokenizers 0.13.2
Downloads last month
8
Safetensors
Model size
242M params
Tensor type
F32
·

Dataset used to train ALM/whisper-it-small

Evaluation results