|
|
--- |
|
|
license: cc-by-4.0 |
|
|
language: |
|
|
- bo |
|
|
--- |
|
|
An OCR model trained on the [GoogleBooks Dataset](https://huggingface.co/datasets/ta4tsering/Google_Books_datasets) using a CRNN architecture. |
|
|
We use the following architecture identifiers: |
|
|
- E: Easter2 (https://huggingface.co/BDRC/GoogleBooks_E_v1) |
|
|
- C: CRNN (this model) |
|
|
- T: TrOCR -> version 1 (https://huggingface.co/BDRC/GoogleBooks_T_v1) and version 2 (https://huggingface.co/BDRC/GoogleBooks_T_v2). Version two is the recommended checkpoint if you want to run inferences. It was trained a little longer using the same data distribution. We keep v1 in oder to evaluate the actual differences on the predictions. |
