metadata

base_model: openai/whisper-base
datasets:
  - fleurs
language:
  - de
library_name: transformers
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Base German Punctuation 4k - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: fleurs
          config: de_de
          split: None
          args: 'config: de split: test'
        metrics:
          - type: wer
            value: 42.652697521196735
            name: Wer

Whisper Base German Punctuation 4k - Chee Li

This model is a fine-tuned version of openai/whisper-base on the Google Fleurs dataset. It achieves the following results on the evaluation set:

Loss: 0.6091
Wer: 42.6527

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 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: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0578	4.7619	1000	0.4862	36.8202
0.0052	9.5238	2000	0.5652	36.5610
0.0028	14.2857	3000	0.5972	41.4808
0.0023	19.0476	4000	0.6091	42.6527

Framework versions

Transformers 4.46.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.20.3