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-german-V2-HanNeurAI
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0 German shuffled 200k rows
          type: mozilla-foundation/common_voice_11_0
          config: de
          split: test
          args: 'config: de, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 32.33273006844562

whisper-tiny-german-V2-HanNeurAI

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: 0.5818
Wer: 32.3327

This fine-tuning model is part of my school project. With limitation of my compute, I scale down the dataset from german common voice to shuffled 200k rows

Additional information can be found in this github: HanCreation/Whisper-Tiny-German

Model description

Model Parameter (pipe.model.num_parameters()): 37760640 (37M)

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-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: 500
training_steps: 8000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2054	0.08	1000	0.7062	39.0698
0.1861	0.16	2000	0.6687	36.4857
0.1677	0.24	3000	0.6393	35.6849
0.2019	0.32	4000	0.6193	34.4385
0.1808	0.4	5000	0.6103	33.8459
0.1697	0.48	6000	0.5956	32.8519
0.1468	0.56	7000	0.5884	32.7029
0.1906	0.64	8000	0.5818	32.3327

Framework versions

Transformers 4.40.2
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1

Intended uses & limitations

More information needed

Training and evaluation data