Whisper Small
This model is a fine-tuned version of rb00/whisper-small-nl-v0.4 on the Common Voice 17.0 dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
For 100 samples:
- wer (dutch_stc_speaker_by_susan_upto_03_jun): 11.5385
- wer (HouseAndZipCodeSpeechgen): 42.2128
- wer (facebook/multilingual_librispeech): 42.1868
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 100
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 18
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.