Hi, I am following this tutorial to generate a language model using the bible data as in example.
https://github.com/kmario23/KenLM-training
I have successfully generated the .arpa file but failed to generate trie file
I am using this command kenlm/bin/build_binary trie bible.arpa bible.binary
and this is the result
Reading bible.arpa ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 Segmentation fault (core dumped)
Please give me some help, I tried another machine with greater specs and clean install but still got the same error.
-
It looks like that repo is not using the original KenLM, maybe use that instead.
-
Youl would only need a trie for older DeepSpeech version. What version do you have?
-
Follow these steps, they should work:
1 Like
- oh, I didnt notice that this is not the original training code, my bad. I will try the original now and report later
- Yes, I am using version 0.6.0 of DeepSpeech
- I will check this out too, thank you for your reply!