You're looking at a specific version of this model. Jump to the model overview.
mind-ware /dots-ocr-with-confidence:fc9faadd
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| image |
string
|
Input image for OCR
|
|
| prompt_mode |
None
|
layout_all
|
Prompt mode
|
| custom_prompt |
string
|
|
Custom prompt (for prompt_mode='custom')
|
| bbox |
string
|
|
Bounding box 'x1,y1,x2,y2' (for prompt_mode='grounding_ocr')
|
| max_tokens |
integer
|
8192
Min: 256 Max: 32768 |
Max tokens
|
| return_confidence |
boolean
|
False
|
Return per-word confidence scores
|
| confidence_threshold |
number
|
0.5
Max: 1 |
Threshold below which words are flagged as low confidence (0-1)
|
| temperature |
number
|
0.1
Max: 2 |
Sampling temperature (ignored when return_confidence=True)
|
| top_p |
number
|
0.9
Max: 1 |
Top-p sampling
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'avg_confidence': {'nullable': True,
'title': 'Avg Confidence',
'type': 'number'},
'bbox_used': {'items': {'type': 'integer'},
'nullable': True,
'title': 'Bbox Used',
'type': 'array'},
'low_confidence_count': {'nullable': True,
'title': 'Low Confidence Count',
'type': 'integer'},
'prompt_mode': {'nullable': True,
'title': 'Prompt Mode',
'type': 'string'},
'text': {'title': 'Text', 'type': 'string'},
'word_confidences': {'items': {'additionalProperties': True,
'type': 'object'},
'nullable': True,
'title': 'Word Confidences',
'type': 'array'},
'word_count': {'nullable': True,
'title': 'Word Count',
'type': 'integer'}},
'required': ['text'],
'title': 'Output',
'type': 'object'}