kmario23 / kenlm-training Goto Github PK
View Code? Open in Web Editor NEWTraining an n-gram based Language Model using KenLM toolkit for Deep Speech 2
Training an n-gram based Language Model using KenLM toolkit for Deep Speech 2
Hi, I got error like in title when running this command:
./kenlm/bin/build_binary trie bible.arpa bible.binary
everything was good until this step, no sign of out of memory or something like that, it crashed immediately
any suggestion?
p/s: if I cant solve this problem, can I just use the arpa file (without trie)? it give the same score with the demo sentence in the README
I am trying to make an arabic language model the problem is the characters are not understandable by many frameworks so I use a simple conversion to map each character to English characters but arabic characters are more than English so there are capital letters in the corpus that will change the meaning if lowered. Will be that an issue to use capital letters?
Hi, a great thanks to the post on how to install kenlm. i have build bible.arpa and able to get the scores of the sentence using model.score(), now i would like to get the suitable n number of words when a character/sentence is given, how to get that.
one more is what are all the functions available for this model, where can i get those functions or arguments
After i run the command :bzcat bible.en.txt.bz2 | python preprocess.py | ./kenlm/bin/lmplz -o 3 > bible.arpa,
ERROR:bash: ./kenlm/bin/lmplz: No such file or directory
Traceback (most recent call last):
File "preprocess.py", line 6, in
print(' '.join(nltk.word_tokenize(sentence)).lower())
BrokenPipeError: [Errno 32] Broken pipe.
Hello
Please I am following this tutorial to create my French Language model : https://github.com/kmario23/KenLM-training
But when I type this cmd :
bzcat ./data_final/vocabulary.txt.bz2 | python preprocess.py | /home/innovation/kenlm/bin/lmplz -o 3 > myvocabulary.arpa
I get the following error :
print(' '.join(nltk.word_tokenize(sentence)).lower())
BrokenPipeError: [Errno 32] Broken pipe
Erreur de segmentation (core dumped)
Hi,
I have successful run all those steps in README and have bible.arpa bible.binary but there is no trie file
How can I generate trie? I cant find any tutorial about this
The original repo is: https://github.com/kpu/kenlm (1600 stars) but the instructions are to clone https://github.com/vchahun/kenlm.git which is a fork with only 5 stars and is 1000 commits behind master.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.