You are using an old version of training command. Please review the wiki
page regarding training again.
Trainng from scratch command will be similar to the following.
training/lstmtraining \
--debug_interval -1 \
--traineddata ~/tesstutorial/engtrain/eng/eng.traineddata \
--net_spec '[1,36,0,1 Ct3,3,16 Mp3,3 Lfys48 Lfx96 Lrx96 Lfx256 O1c111]' \
--learning_rate 20e-4 \
--train_listfile ~/tesstutorial/engtrain/eng.training_files.txt \
--eval_listfile ~/tesstutorial/engeval/eng.training_files.txt \
--model_output ~/tesstutorial/engoutput/base \ --max_iterations 5000
\
&>~/tesstutorial/engoutput/basetrain.log
You need a starter trainedata rather than the unicharset file.
It is easiest if you use tesstrain.sh to create the data files before
running lstmtraining.
ShreeDevi
____________________________________________________________
भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com
On Sat, Jan 13, 2018 at 7:49 AM, Sumedhe Dissanayake <
sumedhedissanay...@gmail.com> wrote:
> I tried lstmtraining with sinhala language but I always get this error.
>
> Command:
>
> lstmtraining --traineddata ~/tesstutorial/sintrain/sin/sin.traineddata \
> --net_spec '[1,36,0,1 Ct3,3,16 Mp3,3 Lfys48 Lfx96 Lrx96 Lfx256 O1c155]'
> \
> --debug_interval 0 --max_iterations 500000 --max_image_MB 60000
> --learning_rate
> 20e-4 \
> --model_output ~/tesstutorial/sinoutput/base \
> -U ~/tesstutorial/sintrain/sin/sin.unicharset \
> --traineddata ~/tesstutorial/sintrain/sin/sin.traineddata \
> --train_listfile ~/tesstutorial/sintrain/sin.training_files.txt
>
>
> Error:
> Can't encode transcription: 'වැනි නිර්භීත දැන් පියඹා මෙන්ම හා' in
> language ''
>
>
>
>
>
> <https://lh3.googleusercontent.com/-OI3Fa2QpWgk/WllqKRXYOBI/AAAAAAAAB1g/6gGg9l6txgItGlpGaAfPa4sNKfHYgL75QCLcBGAs/s1600/Screenshot%2Bfrom%2B2018-01-09%2B21-29-43.png>
>
> I tried with english language also, It worked well with english.
>
> How to resolve this issue?
>
> Platform:
> Linux Ubuntu 16.04 LTS
>
> Tesseract Version:
> tesseract 4.00.00alpha
> leptonica-1.74.4
> libjpeg 8d (libjpeg-turbo 1.4.2) : libpng 1.2.54 : libtiff 4.0.6 : zlib
> 1.2.8 : libwebp 0.4.4 : libopenjp2 2.1.0
>
> --
> 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 tesseract-ocr+unsubscr...@googlegroups.com.
> To post to this group, send email to tesseract-ocr@googlegroups.com.
> Visit this group at https://groups.google.com/group/tesseract-ocr.
> To view this discussion on the web visit https://groups.google.com/d/
> msgid/tesseract-ocr/a6f3ccc4-eb0f-4ab7-a194-90219f499135%
> 40googlegroups.com
> <https://groups.google.com/d/msgid/tesseract-ocr/a6f3ccc4-eb0f-4ab7-a194-90219f499135%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
> For more options, visit https://groups.google.com/d/optout.
>
--
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduUG7%2BD1Jy-BCr99qRcTBqgw_%2BQ8jrbUxSDTphMy-g9%2BJA%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.
