Whisper Tiny Hu v4
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2083
- Wer Ortho: 12.1522
- Wer: 11.2719
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: 4e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
---|---|---|---|---|---|
0.002 | 2.68 | 1000 | 0.2083 | 12.1522 | 11.2719 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 4
Inference API (serverless) is not available, repository is disabled.
Model tree for Hungarians/whisper-tiny-cv16-hu-final
Base model
openai/whisper-tiny
Finetuned
this model
Dataset used to train Hungarians/whisper-tiny-cv16-hu-final
Evaluation results
- Wer on Common Voice 16.0 - Hungariantest set self-reported11.272