mkenfenheuer/whisper-small-de-v3-ct2

This model is a converted version of mkenfenheuer/whisper-small-de-v3 converted to ctranslate2.

Whisper Small DE v3.0 - Maximilian Kenfenheuer

This model is a fine-tuned version of mkenfenheuer/whisper-small-de-v2 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0402
• Wer: 2.4517

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
• training_steps: 1001
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0694	0.9990	1000	0.0402	2.4517

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0