issues
search
Gene-Weaver
/
VoucherVision
Initiated by the University of Michigan Herbarium, VoucherVision harnesses the power of large language models (LLMs) to transform the transcription process of natural history specimen labels.
https://huggingface.co/spaces/phyloforfun/VoucherVision
GNU General Public License v3.0
18
stars
4
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Refactor so that all OCR is performed prior to LLM calls
#40
Gene-Weaver
opened
2 months ago
0
Add support for GOT OCR 2.0
#39
Gene-Weaver
opened
2 months ago
0
Document process for addition of new OCR engine / model
#37
nickynicolson
opened
2 months ago
1
Add support for Qwen2-VL as an OCR engine
#36
nickynicolson
opened
2 months ago
3
Save settings needs to be updated to match most recent config formatting
#35
Gene-Weaver
opened
2 months ago
0
PDFs to jpgs are rotated 90 degrees clockwise the wrong way
#34
Gene-Weaver
opened
2 months ago
0
Make sure the HF Space works with PDFs
#33
Gene-Weaver
closed
2 months ago
1
Create label collage from individual images
#32
Gene-Weaver
closed
2 months ago
0
Estimate API cost for OCR models
#31
mickley
opened
3 months ago
1
Some local LLMs are returning "NoneType" or "str()" errors
#29
Gene-Weaver
opened
3 months ago
0
A way to handle annotation labels
#28
mickley
opened
3 months ago
0
Change API cost representation to cost/million tokens to reflect falling prices
#27
Gene-Weaver
closed
2 months ago
1
Review / update installation instructions reference to anaconda given Anaconda Inc's pursuit of T&C violations
#26
nickynicolson
opened
3 months ago
0
Transition from using PIP to Poetry for package management
#25
Gene-Weaver
opened
3 months ago
0
Bugfix huggingface key and make Google OCR optional
#24
kymillev
closed
3 months ago
0
Using provided fine-tuned Local LLM results in OSError
#23
KaneLindsay
opened
3 months ago
0
Parsing issue with palm2-textunicorn-001
#21
mickley
closed
3 months ago
1
Fix for Gemini 1.5 Pro, Gemini 1.0 pro
#20
mickley
closed
3 months ago
1
Add support for Florence-2 as an OCR engine
#19
Gene-Weaver
closed
2 months ago
0
Add support for Phi-3-vision as an OCR engine
#18
Gene-Weaver
closed
2 months ago
1
Add support for GPT-4o-mini for LLM and OCR
#17
Gene-Weaver
closed
2 months ago
0
Docker / Containerize
#16
Gene-Weaver
opened
4 months ago
0
Add command line interface
#15
Gene-Weaver
opened
4 months ago
0
Update requirements.txt add mistralai
#8
nickynicolson
closed
3 months ago
1
Add mistralai to requirements.txt
#7
nickynicolson
closed
4 months ago
0
Consider supporting groq
#6
nickynicolson
opened
5 months ago
1
Bundle raw OCR results with VV parsing results
#5
jbest
opened
11 months ago
0
API Request
#4
jbest
opened
11 months ago
2
Importing OCR and/or running OCR step separately. (Suggestion/Question)
#3
norbo27
opened
12 months ago
1
Documentation update: can the necessary API keys be set as environment variables?
#2
nickynicolson
closed
9 months ago
2
Test to confirm operation of individual APIs
#1
jbest
closed
1 year ago
2