Downloads · 30 days
22
37% of all-time downloads
cyttic/trocr-noise-bigram2-s42
trocr-noise-bigram2-s42 is a image-text-to-text model from cyttic. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
22
37% of all-time downloads
All-time downloads
59
Public
Parameters
299M
3.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of cyttic/exp2-frozen-benyehuda-cont on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 4.7577 | 0.1290 | 2000 | 2.2867 | 0.2197 | 0.4316 |
| 3.7215 | 0.2581 | 4000 | 1.8651 | 0.1788 | 0.3436 |
| 2.8897 | 0.3871 | 6000 | 1.3412 | 0.1033 | 0.2385 |
| 2.4471 | 0.5161 | 8000 | 1.0767 | 0.0803 | 0.1952 |
| 2.0402 | 0.6452 | 10000 | 0.9400 | 0.0677 | 0.1703 |
| 1.8687 | 0.7742 | 12000 | 0.8237 | 0.0559 | 0.1417 |
| 1.7395 | 0.9032 | 14000 | 0.7464 | 0.0511 | 0.1298 |
| 1.2768 | 1.0323 | 16000 | 0.6948 | 0.0461 | 0.1197 |
| 1.2211 | 1.1613 | 18000 | 0.6468 | 0.0414 | 0.1100 |
| 1.1001 | 1.2903 | 20000 | 0.6070 | 0.0374 | 0.1014 |
| 1.0172 | 1.4194 | 22000 | 0.5774 | 0.0345 | 0.0945 |
| 1.1212 | 1.5484 | 24000 | 0.5458 | 0.0327 | 0.0884 |
| 1.0263 | 1.6774 | 26000 | 0.5250 | 0.0311 | 0.0855 |
| 0.9562 | 1.8065 | 28000 | 0.4989 | 0.0289 | 0.0793 |
| 0.9331 | 1.9355 | 30000 | 0.4819 | 0.0269 | 0.0762 |
| 0.7016 | 2.0645 | 32000 | 0.4640 | 0.0266 | 0.0736 |
| 0.7349 | 2.1935 | 34000 | 0.4522 | 0.0258 | 0.0712 |
| 0.6888 | 2.3226 | 36000 | 0.4478 | 0.0244 | 0.0682 |
| 0.6980 | 2.4516 | 38000 | 0.4353 | 0.0238 | 0.0664 |
| 0.6809 | 2.5806 | 40000 | 0.4250 | 0.0219 | 0.0637 |
| 0.6996 | 2.7097 | 42000 | 0.4211 | 0.0225 | 0.0635 |
| 0.7074 | 2.8387 | 44000 | 0.4137 | 0.0221 | 0.0632 |
| 0.7260 | 2.9677 | 46000 | 0.4118 | 0.0216 | 0.0621 |
| 0.6683 | 3.0 | 46500 | 0.4117 | 0.0215 | 0.0622 |