add vision processor
This commit is contained in:
@@ -2,13 +2,17 @@
|
||||
opencv-python>=4.8.0
|
||||
Pillow>=10.0.0
|
||||
|
||||
# OCR engines (install at least one)
|
||||
# Tesseract (recommended, lightweight)
|
||||
# Vision analysis (recommended for better results)
|
||||
# Requires Ollama to be installed: https://ollama.ai/download
|
||||
ollama>=0.1.0
|
||||
|
||||
# OCR engines (alternative to vision analysis)
|
||||
# Tesseract (lightweight, basic text extraction)
|
||||
pytesseract>=0.3.10
|
||||
|
||||
# Alternative OCR engines (optional, install as needed)
|
||||
# Alternative OCR engines (optional)
|
||||
# easyocr>=1.7.0
|
||||
# paddleocr>=2.7.0
|
||||
|
||||
# For Whisper transcription (if not already installed)
|
||||
# For Whisper transcription (recommended)
|
||||
# openai-whisper>=20230918
|
||||
|
||||
Reference in New Issue
Block a user