LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

What model to “transcribe notes”? (alien.top)

submitted 11 months ago by olddoglearnsnewtrick@alien.top to c/localllama@poweruser.forum

5 comments fedilink hide all child comments

I have a large corpus of notes humans wrote to summarize articles. As is they will give you the gist but are not very readable. I would like to use a gen model and ask “please write a short sentence that will be nice to read describing the following facts” and feed it the notes, to obtain a brief readable summary.

Language is Italian.

Suggestions on models or workflows?

Thanks

you are viewing a single comment's thread
view the rest of the comments

[–] AI_Trenches@alien.top 1 points 11 months ago (2 children)

You can try taking a picture of the notes and having a multimodal model try and read and extracts its text. You can either use chatgpt4(paid but probably more accurate) or run llama.cpp llava multimodal function with a llava model locally(free but might hallucinate).

Maybe scanning your notes into PDF format and trying a RAG approach might yield some results too. You can upload the PDF to GPT/Claude or run a local RAG project like h2oGPT or privategpt and see how well they can transcribe your notes.

[–] shreydanfr@alien.top 1 points 11 months ago

I doubt gpt4V will be perfect at reading detailed handwritten notes that too in Italian. For proper results, google lens is good at handwritten structured OCR, but needs manual work.

load more comments (1 replies)