Skip to content

OCR detection error #442

Description

@aragorne6

Hello,

I use the program with the GPU under Linux cachyOS with the default OCR to translate from English to French, and I translate using the LM Studio API (openAI-compatible).

When I save the raw text, here's the content:

{
"block_0": "",

"block_1": "",

"block_2": ""

}

The image contains the text "Hm, another new bag? She's been splurging a lot lately."
The program sends this to LM Studio:

"choices": [
{

"index": 0,

"message": {

"role": "assistant",

"content": "{\n \"block_0\": \"\",\n \"block_1\": \"\",\n \"block_2\": \"\"\n}",

"reasoning_content": "",

"tool_calls": []

},

"logprobs": null,

"finish_reason": "stop"

onnxruntime-gpu 1.24.4
Cuda 12.9
Cudnn 9.10
Tensorrt 10.16.0.72

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions