Declined
7
[Feature Request] Idea: Hardware Accelerated OCR Workers (NPU/GPU)
Source: paperless-ngx/paperless-ngx#11939 · opened by @Ncard00123
Description
Hi Paperless-ngx Team,
Many users run Paperless on modern hardware with idle NPUs or GPUs. I’d like to suggest adding a worker option for hardware-accelerated OCR (e.g., via specialized Docker images for NVIDIA or Apple Silicon).
This would significantly reduce "consumption" time for users importing large archives of PDFs and images.
Other
_No response_
Hi Paperless-ngx Team,
Many users run Paperless on modern hardware with idle NPUs or GPUs. I’d like to suggest adding a worker option for hardware-accelerated OCR (e.g., via specialized Docker images for NVIDIA or Apple Silicon).
This would significantly reduce "consumption" time for users importing large archives of PDFs and images.
Other
_No response_
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature Request] Support a self-hostable remote OCR service
30 votes · 0 comments
[Feature] Optional removal of blank pages from the archive file (originals untouched)
1 vote · 0 comments
[Feature Request] OCR: Extract specific data from zones into Fields [PR incoming]
12 votes · 0 comments
[Feature Request] Make Remote OCR respect `PAPERLESS_OCR_MODE` and local preprocessing options
5 votes · 0 comments
[Feature Request] OCR rendition on linked documents
2 votes · 0 comments
No comments yet.