OCR for Vedic texts printed in Devanagari.
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Schroeder's edition of Maitrāyaṇī Sam̐hitā:
https://huggingface.co/datasets/yzk/veda-ocr-ms (will be public)
1params:
2 max_length: 512
3 train_batch_size: 16
4 eval_batch_size: 16
5 learning_rate: 2e-5
6 weight_decay: 0.01
7 save_total_limit: 3
8 num_train_epochs: 20
9 logging_steps: 2
10 save_steps: 2000
11 eval_steps: 200
