1
[Feature] Multi Model OCR
Source: immich-app/immich#24077 · opened by @TNieuwdorp
I have searched the existing feature requests, both open and closed, to make sure this is not a duplicate request.
• Yes
The feature
When a gallery contains two languages that are not covered by a single PaddleOCR model ([in my case English and Dutch]( which would require both "latin" and any model that covers English) it is currently not possible to index both languages automatically, since only one OCR model can be set in the settings. My request to be to make the OCR model job-dependant, so you can add a second OCR job that runs a different model so both languages can be indexed automatically.
Many thanks for putting together such an amazing product. You've built the best open source self-hosted Photos app out there, and I'm very thankful that you have.
Platform
• Server
• Web
• Mobile
• Yes
The feature
When a gallery contains two languages that are not covered by a single PaddleOCR model ([in my case English and Dutch]( which would require both "latin" and any model that covers English) it is currently not possible to index both languages automatically, since only one OCR model can be set in the settings. My request to be to make the OCR model job-dependant, so you can add a second OCR job that runs a different model so both languages can be indexed automatically.
Many thanks for putting together such an amazing product. You've built the best open source self-hosted Photos app out there, and I'm very thankful that you have.
Platform
• Server
• Web
• Mobile
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature] Allow re-running OCR for a single asset
1 vote · 0 comments
[Feature] Add Baidu/Unlimited-OCR as an OCR option
2 votes · 0 comments
[Feature] Translate OCR recognized text to target language using machine learning
2 votes · 0 comments
[Feature] OCR hw acceleration for Rockchip boards
2 votes · 0 comments
[Feature] Add Persian (Farsi) OCR support
2 votes · 0 comments
No comments yet.