Whisper-tiny code-switching czech vietnamese
This model is a fine-tuned version of openai/whisper-tiny on the Test set kvuli testovani rovnou pri treninku dataset. It achieves the following results on the evaluation set:
- Loss: 1.1536
- Wer: 58.3805
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.0008 | 30.02 | 990 | 1.1134 | 58.6752 |
0.0004 | 61.01 | 1980 | 1.1536 | 58.3805 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 2
Finetuned from
Dataset used to train xbilek25/whisper-base-train-250-2000
Evaluation results
- Wer on Test set kvuli testovani rovnou pri treninkuself-reported58.380