Image-to-Text
Transformers
Safetensors
English
Russian
pp_ocrv6_small_rec
captcha
ocr
minecraft
pp-ocrv6
text-recognition
cyrillic
Instructions to use Titlehhhh/captchaocr-ppocrv6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Titlehhhh/captchaocr-ppocrv6 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="Titlehhhh/captchaocr-ppocrv6")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Titlehhhh/captchaocr-ppocrv6", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download finetune_meta.json from Titlehhhh/captchaocr-ppocrv6: direct link, hf CLI and curl.
- Browser
- Download file 507 Bytes
-
https://huggingface.co/Titlehhhh/captchaocr-ppocrv6/resolve/main/finetune_meta.json
- Command line
-
hf download hf://Titlehhhh/captchaocr-ppocrv6/finetune_meta.json
-
curl -L -o finetune_meta.json https://huggingface.co/Titlehhhh/captchaocr-ppocrv6/resolve/main/finetune_meta.json
507 Bytes
| { | |
| "base_model": "PaddlePaddle/PP-OCRv6_medium_rec_safetensors", | |
| "checkpoint": "C:\\Users\\Title\\Projects\\CapthaModel\\train\\runs\\ppocrv6\\universal_v1\\best.pt", | |
| "epoch": 4, | |
| "step": 2440, | |
| "soup_alpha": 1.0, | |
| "classes": 18762, | |
| "parameters": 19186154, | |
| "tensors": 308, | |
| "normalisation": { | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ] | |
| }, | |
| "transformers_class": "PPOCRV6SmallRecForTextRecognition", | |
| "exported_by": "train\\export_ppocr_hf.py" | |
| } |