README.md

metadata

language:
  - de
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Tiny De
    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: test
          args: 'config: de, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 34.35027563247207

Whisper Tiny De

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

• Loss: 0.4460
• Wer: 34.3503

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: 3.75e-05
• train_batch_size: 16
• eval_batch_size: 8
• 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: 7500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.369	0.33	2500	0.6042	63.0444
0.5022	0.67	5000	0.4967	34.7095
0.271	1.0	7500	0.4460	34.3503

Framework versions

• Transformers 4.34.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.6.dev0
• Tokenizers 0.13.3