Is it possible to make speech to text with pythonista to print to the console,

Or also displaying it as a textsprite thingy

Cool awesome Thanks this worked I did not know you could use for twice in one line of code

a=[‘Haloween’, ‘Boom’, ‘hi’, ‘Howl’, ‘if’, ‘ghosts’]
B=[s[i:i+2] for s in a for i in range(0, len(s), 2)]
Print(B)

I have a question about a list of strings

Say I got a list like

a=[‘Haloween’, ‘Boom’, ‘hi’, ‘Howl’, ‘if’, ‘ghosts’]

How do you split or slice the strings to make a list like

a=[‘Ha’, ‘lo’, ‘we’, ‘en’, ‘Bo’, ‘om’, ‘hi’, ‘Ho’, ‘wl’, ‘if’, ‘gh’, ‘os’, ‘ts’]

Is this possible to do?

Question 1
Are you able to pip install opencv cv2 with stash?

Question 2
Are you able to install tessaract and pytessaract with stash?

Question 3
Does pythonista 3 come with Core ML already or does it need to be installed?

I have a quick question in regards to the original ocr post how do I print the text as one single csv list, I tried but I have been getting a list of lists instead of one single list

This is a snippet of the code example I think needs to be altered

  success = handler.performRequests_error_([req], None)
    if success:
        for result in req.results():
            print(result.text())
    else:
        print('Problem recognizing anything')

ive seen the apple documentation coding on Vision Framework I just dont know how to convert it to python

Question 1
What about the setting the minimum text height how do you translate either of these codes to python????
@property(readwrite, nonatomic, assign) float minimumTextHeight; written in objective-c
var minimumTextHeight: Float { get set } written in Swift

Question 2
I was also interested in learning how to recognize the individual boxes from a sudoku puzzle to extract the numbers is there a way to do that possibly with
VNRecognizedTextObservation A request that detects and recognizes regions of text in an image.
or possibly with the bounding box technique show in the video https://developer.apple.com/videos/play/wwdc2019/234 , also can you put multiple bounding boxes to recognize text from a sudoku card

this is Mikeals code i am trying to insert the code into but dont know how to convert the code shown in the apple documentation into python

language_preference = ['fi','en','se']

import photos, ui, dialogs
import io
from objc_util import *

load_framework('Vision')
VNRecognizeTextRequest = ObjCClass('VNRecognizeTextRequest')
VNImageRequestHandler = ObjCClass('VNImageRequestHandler')

def pil2ui(pil_image):
    buffer = io.BytesIO()
    pil_image.save(buffer, format='PNG')
    return ui.Image.from_data(buffer.getvalue())

selection = dialogs.alert('Get pic', button1='Camera', button2='Photos')

ui_image = None

if selection == 1:
    pil_image = photos.capture_image()
    if pil_image is not None:
        ui_image = pil2ui(pil_image)
elif selection == 2:
    ui_image = photos.pick_asset().get_ui_image()

if ui_image is not None:
    print('Recognizing...\n')

    req = VNRecognizeTextRequest.alloc().init().autorelease()
    req.recognitionLevel=1
    req.setRecognitionLanguages_(language_preference)
    handler = VNImageRequestHandler.alloc().initWithData_options_(ui_image.to_png(), None).autorelease()

    success = handler.performRequests_error_([req], None)
    if success:
        for result in req.results():
            print(result.text())
    else:
        print('Problem recognizing anything')

I have a few questions about the very first text recognition code posted on this one

the example video I am referring to is https://developer.apple.com/videos/play/wwdc2019/234

1 how do you change the recognition level from fast to accurate
example code from apple website I am not sure if its written in swift or objective c but it is like this :

myTextRegcognitionRequest.recognitionLevel = VNRequestTextRecognitionLevel.accurate

and another example of this shown in the apple video for setting the recognition level

 request.recognitionLevel = .fast 

question 2
to ensure that numbers don't get mistaken as letters
without the language corrector active to avoid mistaking the number 5 for an S or I as 1
example of this from the video is

extension Character {
       
     func GetSimilarCharacterIfNotIn(allowedChars: String -> Character {
            let  conversionTable = [
                      's':'5',
                      'S':'5',
                      'i':'1',
                      'I':'1', ] 

question 3
if you know how to set up the special words detector thingy feature mentioned in the video

I need help adapting this script for inputting the numbers from a picture of sudoku and insert the starting numbers into a console script, it does not work good for recognizing ones and sevens???

Example of sudoku solver

In my version I want to make the board is all zeros and when you take a picture it will add the numbers than solve, this combines the two programs (sudoku solver) & (ocr text recognition)

board=[
   [5,8,4,1,0,0,0,0,0],
   [0,0,6,8,0,0,5,1,0],
   [0,0,0,0,5,4,7,0,6],
   [0,5,3,0,1,0,0,6,7],
   [0,0,0,0,2,0,0,0,0],
   [4,6,0,0,9,0,8,3,0],
   [7,0,8,5,4,0,0,0,0],
   [0,2,9,0,0,3,4,0,0],
   [0,0,0,0,0,1,3,7,9]
   ]



def solve(bo):

   find = find_empty(bo)
   if not find:
       return True
   else:
       row,col = find

   for i in range(1,10):
       if valid(bo,i,(row,col)):
           bo[row][col] = i

           if solve(bo):
               return True

           bo[row][col] = 0

   return False



def valid(bo,num,pos):
   #check row
   for i in range(len(bo[0])):
       if bo[pos[0]][i] == num and pos[1] != i:
           return False
   #check column
   for i in range(len(bo[0])):
       if bo[i][pos[1]] == num and pos[0] != i:
           return False
   #check quadrant
   box_x = pos[1] // 3
   box_y = pos[0] // 3

   for i in range(box_y * 3, box_y * 3 + 3):
       for j in range(box_x * 3, box_x * 3 + 3):
           if bo[i][j] == num and (i,j) != pos:
               return False

   return True



def print_board(bo):
   for i in range(len(bo)):
       if i % 3 == 0 and i != 0:
           print('------+-------+------')

       for j in range(len(bo[0])):
           if j % 3 == 0 and j != 0:
               print('|',end=' ')
           if j == 8:
               print(bo[i][j])
           else:
               print(str(bo[i][j])+ ' ', end='')

def find_empty(bo):
   for i in range(len(bo)):
       for j in range(len(bo[0])):
           if bo[i][j] == 0:
               return (i,j) # row, col
   return None



print_board(board)
solve(board)
print('=====================')
print_board(board)

language_preference = ['fi','en','se']

import photos, ui, dialogs
import io
from objc_util import *

load_framework('Vision')
VNRecognizeTextRequest = ObjCClass('VNRecognizeTextRequest')
VNImageRequestHandler = ObjCClass('VNImageRequestHandler')

def pil2ui(pil_image):
   buffer = io.BytesIO()
   pil_image.save(buffer, format='PNG')
   return ui.Image.from_data(buffer.getvalue())

selection = dialogs.alert('Get pic', button1='Camera', button2='Photos')

ui_image = None

if selection == 1:
   pil_image = photos.capture_image()
   if pil_image is not None:
       ui_image = pil2ui(pil_image)
elif selection == 2:
   ui_image = photos.pick_asset().get_ui_image()

if ui_image is not None:
   print('Recognizing...\n')

   req = VNRecognizeTextRequest.alloc().init().autorelease()
   req.setRecognitionLanguages_(language_preference)
   handler = VNImageRequestHandler.alloc().initWithData_options_(ui_image.to_png(), None).autorelease()

   success = handler.performRequests_error_([req], None)
   if success:
       for result in req.results():
           print(result.text())
   else:
       print('Problem recognizing anything') ```

I will test it for sudoku in the console, well I will try to convert it to use in console for the sudoku solver if need help I’ll post a message

So there are a few edits in this thread I don’t know how to piece together to have the best edited version of this???