metadata

library_name: transformers
language:
  - de
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Base De - Krish Kalra
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: de
          split: None
          args: 'config: de, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 24.248050501299666

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