Whisper Tiny Hu v6
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: 0.1880
- Wer Ortho: 11.4928
- Wer: 10.6137
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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: 2000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
---|---|---|---|---|---|
0.0036 | 5.35 | 1000 | 0.1855 | 12.1161 | 11.2185 |
0.0004 | 10.71 | 2000 | 0.1880 | 11.4928 | 10.6137 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 2
Finetuned from
Dataset used to train sarpba/whisper-tiny-cv16-hu-v6
Evaluation results
- Wer on Common Voice 16.0 - Hungariantest set self-reported10.614