We may make this public in the future but will need significant clean up first. Relies too heavily on our internal infrastructure currently so might be too difficult to run.
Ryan Chesler
emelryan
AI & ML interests
None yet
Recent Activity
new activity 12 days ago
nvidia/nemotron-ocr-v2:will the codes for modified synthdog pipeline be made available? commentedon an article 12 days ago
Building a Fast Multilingual OCR Model with Synthetic DataOrganizations
Normalize Nemotron Parse images in the processor for vLLM compatibility
1
#6 opened 9 days ago
by 
nvidia-oliver-holworthy
will the codes for modified synthdog pipeline be made available?
2
#4 opened 13 days ago
by 
kingjuno
commented on Building a Fast Multilingual OCR Model with Synthetic Data 12 days ago
updated 2
models 13 days ago
add-json-csv-table-formats
#5 opened 13 days ago
by emelryan
does this support word-by-word detection instead of line-by-line for multi??
4
#3 opened 19 days ago
by 
hnyll
Update with support for transformers 5.x compatibility
1
#4 opened 18 days ago
by nvidia-oliver-holworthy
updated a
dataset 20 days ago
upvoted an article 23 days ago
Article
Building a Fast Multilingual OCR Model with Synthetic Data
•
32
published an article 23 days ago
Article
Building a Fast Multilingual OCR Model with Synthetic Data
•
32
published a
dataset 23 days ago
updated 2
models 25 days ago
liked 2
models 26 days ago
Failing build of NemotronOCRV2 on arm64
2
#1 opened 29 days ago
by 
kyuukyuutai
Update build-extension to allow arm compilation
#2 opened 28 days ago
by emelryan
updated a
Space about 1 month ago
liked a
Space about 1 month ago