Whisper Small Th - ktc17
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2539
- eval_wer: 119.0783
- eval_runtime: 6397.4314
- eval_samples_per_second: 1.725
- eval_steps_per_second: 0.216
- epoch: 3.09
- step: 2000
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: 64
- 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.2.dev0
- Tokenizers 0.15.0
- Downloads last month
- 0