HackerTrans
トップ新着トレンドコメント過去質問紹介求人

avibhu

no profile record

コメント

avibhu
·2 年前·議論
Ironic name.
avibhu
·2 年前·議論
Have you tried few shot prompting? Something on the lines of:

User: Extract x from the given scanned document. <sample_img_1>

Assistant: <sample_img_1_output>

User: Extract x from the given scanned document. <sample_img_2>

Assistant: <sample_img_2_output>

User: Extract x from the given scanned document. <query_image>

In my experience, this seems to make the model significantly more consistent.
avibhu
·3 年前·議論
For what its worth, very high quality OCR from Google's Vision offering costs $0.0015 per page, with 1000 free pages per month. In my experience, it has been signficantly superior to any open source solution.
avibhu
·3 年前·議論
Can you share that string please?
avibhu
·3 年前·議論
Tangential: you can finetune something like flan-ul2 to do quote extraction using examples generated from chatgpt. If you have a good enough GPU, it should help cut down costs significantly
avibhu
·3 年前·議論
Not sure why there no direct replies to this, but 108 is a dedicated line for all emergencies. Interestingly 112 and 911 have also worked for me in the past when butt dialed.