Instructions to use microsoft/trocr-small-printed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/trocr-small-printed 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="microsoft/trocr-small-printed")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-small-printed") model = AutoModelForImageTextToText.from_pretrained("microsoft/trocr-small-printed") - Notebooks
- Google Colab
- Kaggle
ValueError: Unrecognized feature extractor in microsoft/trocr-base-handwritten. Should have a `feature_extractor_type` key in its preprocessor_config.json of config.json, or one of the following `model_type` keys in its {CONFIG_NAME}: {', '.join(c for c in FEATURE_EXTRACTOR_MAPPING_NAMES.keys())}
Browse files- preprocessor_config.json +1 -1
preprocessor_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"do_center_crop": false,
|
| 4 |
"do_normalize": true,
|
| 5 |
"do_resize": true,
|
| 6 |
-
"
|
| 7 |
"image_mean": [
|
| 8 |
0.5,
|
| 9 |
0.5,
|
|
|
|
| 3 |
"do_center_crop": false,
|
| 4 |
"do_normalize": true,
|
| 5 |
"do_resize": true,
|
| 6 |
+
"feature_extractor_type": "DeiTImageProcessor",
|
| 7 |
"image_mean": [
|
| 8 |
0.5,
|
| 9 |
0.5,
|