import subprocess
# List of font names
font_names = ['ben']
for font in font_names:
command = f"lstmtraining --continue_from
data/ben/checkpoints/ben_19.535_298_300.checkpoint --traineddata
data/ben/ben.traineddata --model_output data/ben/checkpoints/ben
--train_listfile data/ben/list.train --eval_listfile data/ben/list.eval
--max_iterations 1000"
subprocess.run(command, shell=True)
i fixed the problem and this code work for me by adding the checkpoint.
On Thursday, 20 July, 2023 at 7:51:43 am UTC+6 Ali hussain wrote:
> I'm new in Tesseract and trying to train my own fonts on Tesseract 5.3.2
> but I have to know if the electricity is cut off or if I cancel vs code or
> something like that of the process of training then if I run the training
> command again so after that it starts from begging or from electricity cut
> off?
>
> I have already to tested it but every time starts from begging. so I need
> to know any method to apply this problem to handle this. because it takes a
> lot of time and is not necessary to start by begging every time or it's
> normal?
>
>
> I use this command to create text-to-image.tif files for multiple fonts in
> Tesseract 5.3.2:
>
> import os
> import random
> import pathlib
> import subprocess
>
> training_text_file = 'langdata/ben.training_text'
> font_list = ['FL Badhon Ansari Rh. Unicode',
> 'F Khairuddin Barbarusa Rah. Uni',
> 'F Mahfuj Art Unicode Italic',
> 'F Mahfuj Art Unicode',
> 'FL Niribili Plain Unicode',
> 'FL Niribili Plain Unicode Itali Italic'
> ] # Add more fonts as needed
>
> lines = []
>
> with open(training_text_file, 'r') as input_file:
> for line in input_file.readlines():
> lines.append(line.strip())
>
> output_directory = 'tesstrain/data/ben-ground-truth'
>
> if not os.path.exists(output_directory):
> os.mkdir(output_directory)
>
> random.shuffle(lines)
>
> count = 100
>
> lines = lines[:count]
>
> line_count = 0
> for line in lines:
> for font in font_list:
> training_text_file_name = pathlib.Path(training_text_file).stem
> line_training_text = os.path.join(
> output_directory,
> f'{training_text_file_name}_{line_count}.gt.txt')
> with open(line_training_text, 'w') as output_file:
> output_file.writelines([line])
>
> file_base_name = f'ben_{line_count}'
>
> subprocess.run([
> 'text2image',
> f'--font={font}',
> f'--text={line_training_text}',
> f'--outputbase={output_directory}/{file_base_name}',
> '--max_pages=1',
> '--strip_unrenderable_words',
> '--leading=32',
> '--xsize=3600',
> '--ysize=350',
> '--char_spacing=1.0',
> '--exposure=0',
> '--unicharset_file=langdata/ben.unicharset'
> ])
>
> line_count += 1
>
>
>
> and this command is for training :
>
> import subprocess
>
> # List of font names
> font_names = ['ben']
>
> for font in font_names:
> command = f"TESSDATA_PREFIX=../tesseract/tessdata make training
> MODEL_NAME={font} START_MODEL=ben TESSDATA=../tesseract/tessdata
> MAX_ITERATIONS=10000 LANG_TYPE=Indic"
> subprocess.run(command, shell=True)
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/a689490c-ebe5-4a3f-8bf2-d7146c841267n%40googlegroups.com.
