Anyone knows how the models do on Russian cursive?
The writing is on the wall for handwriting recognition
51–60 of 116 posts
Re: The writing is on the wall for handwriting recognition
#52Earlier quoted context omitted.
Shhhhh no one cares about data contamination anymore.
Then write something down yourself and upload a picture to gemini.google.com or chatgpt. Hell, combine it. Make yourself a quick math test, print it, solve with pen and ask these models to correct it. They're very good at it.
For that to be relevant to this post, they would need to write with secretary hand.
Re: The writing is on the wall for handwriting recognition
#53Anyone knows how the models do on Russian cursive?
Ultimate Test
Re: The writing is on the wall for handwriting recognition
#54Call me when it can do Russian Cursive.
Right, it can do modern writing but anything older than a century ( church records and census)and it produces garbage. Yandex Archives figured that out and have CER in a single digit but they have the resources to collect immense data for training. I'm slowly building a dataset for finetuning TROCR model and the best it can do is CER 18% ... which is sort of readable.
How do you do, fellow TrOCR fine-tuner?
I'm using TrOCR because it's a smaller model that I can fine tune on a consumer card, but the age of the model and resources certainly make it a challenge. The official notebook for fine tuning hasn't been updated in years and has several errors due to the march of progress in the primary packages.
Re: The writing is on the wall for handwriting recognition
#55Maybe for English, for the other human languages I use, it is still kind of hit and miss, just like speaking recognition, even with English it suffices to have an accent that is off the standard TV one.
Agree here. I've had successes with 18th century Dutch, but again quite a few failures and mistakes
Re: The writing is on the wall for handwriting recognition
#56Call me when it can do Russian Cursive.
Seems to do an OK job: https://g.co/gemini/share/e173d18d1d80 This is a random image from Twitter with no transcript or English translation provided, so it's not going to be in the training data.
This is a historical church document from 19th century and Gemini got it right with common words but completely hallucinated the names of village and people.
Re: The writing is on the wall for handwriting recognition
#57Earlier quoted context omitted.
ee lay vhen!
They don't do Scottish accents!
Indeed, has it improved anything in 14 years?
Re: The writing is on the wall for handwriting recognition
#58Quite certain my doctor can still produce writing, that the models don't stand a chance to be able to recognize.
Re: The writing is on the wall for handwriting recognition
#59Earlier quoted context omitted.
Regular handwriting there are many. Historical handwriting, Gemini 3 is the only one which gave a decent result on a 19th century minutes from a town court in Northern Norway (Danish gothic handwriting with bleed through). I'm not 100% sure it's correct, but that's because it's so dang hard to read it to verify it. At least I see it gets many names, dates and locations right. I've been waiting a long time for this.
> Regular handwriting there are many. Please share. I am out of the loop and my searches have not pointed me to the state of the art, which has seen major steps forward in the past 3 or 4 years but most of it seems to be closed or attached to larger AI products. Is it even still called OCR?
The best open source OCR model for handwriting in my experience is surya-v2 or nougat, really depends on the docs which is better, each got about 90% accuracy (cosine similarity) in my tests. I have not tried Deepseek-OCR, but mean to at some point.
Re: The writing is on the wall for handwriting recognition
#60Surely the true prize is to be able to ditch computers altogether and just write with pencil on paper.
Keyboards are faster.