Whisper Base De - Krish Kalra

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: 0.4592
  • Wer: 24.2481

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
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.4712 1.0 283 0.4442 26.1604
0.46 2.0 566 0.4376 23.1155
0.1985 3.0 849 0.4449 28.6669
0.1576 4.0 1132 0.4542 24.2852
0.0695 5.0 1415 0.4592 24.2481

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
6
Safetensors
Model size
72.6M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Krish03/whisper-base-de

Finetuned
(434)
this model

Dataset used to train Krish03/whisper-base-de

Evaluation results