mkenfenheuer/whisper-small-de-v2-int8-ct2
03
This model is a converted version of mkenfenheuer/whisper-small-de-v2 converted to ctranslate2 with int8 quantization.
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Whisper Small DE v2.0 - Maximilian Kenfenheuer
This model is a fine-tuned version of mkenfenheuer/whisper-small-de on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0607
- Wer: 3.6092
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
- trainbatchsize: 16
- evalbatchsize: 8
- seed: 42
- optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: linear
- training_steps: 1001
- mixedprecisiontraining: Native AMP
Training results
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0