Jamin20's picture
Upload README.md
8c57e63
|
raw
history blame
2.17 kB
metadata
language:
  - de
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-fine-tuned-de_arga
    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: validation[2000:4000]
          args: 'config: german, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 13.547131036720566

whisper-fine-tuned-de_arga

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

  • Loss: 0.3381
  • Wer: 13.5471

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1278 1.6 1000 0.2690 13.9852
0.0155 3.2 2000 0.3036 13.5417
0.0035 4.8 3000 0.3180 13.4985
0.0012 6.4 4000 0.3335 13.5634
0.001 8.0 5000 0.3381 13.5471

Framework versions

  • Transformers 4.27.0.dev0
  • Pytorch 1.13.1
  • Datasets 2.8.0
  • Tokenizers 0.13.2