marccgrau's picture
update model card README.md
43157db
metadata
language:
  - de
license: apache-2.0
tags:
  - sbb-asr
  - generated_from_trainer
datasets:
  - marccgrau/sbbdata_allSNR
metrics:
  - wer
model-index:
  - name: Whisper Small German SBB all SNR - v2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: SBB Dataset 05.01.2023
          type: marccgrau/sbbdata_allSNR
          args: 'config: German, split: train, test, val'
        metrics:
          - name: Wer
            type: wer
            value: 0.18325935320228282

Whisper Small German SBB all SNR - v2

This model is a fine-tuned version of openai/whisper-small on the SBB Dataset 05.01.2023 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4018
  • Wer: 0.1833

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-06
  • 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: 100
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
2.6097 0.71 100 0.9753 0.7838
0.754 1.42 200 0.6018 0.6906
0.5414 2.13 300 0.4864 0.5149
0.4521 2.84 400 0.4234 0.2372
0.4131 3.55 500 0.4018 0.1833

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.1
  • Datasets 2.8.0
  • Tokenizers 0.12.1