10th_science_ta_to_eng
This model is a fine-tuned version of openai/whisper-base on the 10th_science_tamil_to_english dataset. It achieves the following results on the evaluation set:
- eval_loss: 4.2536
- eval_wer: 133.3041
- eval_runtime: 194.5706
- eval_samples_per_second: 1.994
- eval_steps_per_second: 0.128
- epoch: 13.0
- step: 5000
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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.10.2.dev0
- Tokenizers 0.13.2