Conversation
Blurry Moon
sun@shitposter.world
open source OCR is terrible, I used Google Cloud to translate and that worked a lot better.
3
0
0
Q.U.I.N.N.
icedquinn@blob.cat
@sun tesseract isn't great. there are qwen models and such that do ok.
GLM has one that can read handwriting BUT it requires you to have already pre-processed the input with another model :/
GLM has one that can read handwriting BUT it requires you to have already pre-processed the input with another model :/
1
0
2
Blurry Moon
sun@shitposter.world
@snacks I tried about three different things and using the google cloud document api is the only thing that worked acceptably.
1
0
1
1
0
0
Blurry Moon
sun@shitposter.world
0
0
2
mangeurdenuage 
🌿 
mangeurdenuage@shitposter.world
@sun
>open source OCR is terrible
>I used Google Cloud to translate
>to translate
What ? OCR isn't about translating.
All the free/libre OCR I know just work.
>open source OCR is terrible
>I used Google Cloud to translate
>to translate
What ? OCR isn't about translating.
All the free/libre OCR I know just work.
1
0
0
@mangeurdenuage translate to text, sorry that's confusing terminology but technically correct.
1
0
0
mangeurdenuage 🌿
mangeurdenuage@shitposter.world
@icedquinn @sun
>tesseract isn't great
I must live in another dimension but for me it works flawlessly. the last time I had to use it and that was 3 years ago.
>tesseract isn't great
I must live in another dimension but for me it works flawlessly. the last time I had to use it and that was 3 years ago.
2
0
0
mangeurdenuage 🌿
mangeurdenuage@shitposter.world
@sun
Have you tried the FF translation model ?
Have you tried the FF translation model ?
0
0
0
@mangeurdenuage @icedquinn I'm doing japanese
1
0
1
0
0
0