Error: Can't parse trie file, invalid header. Try updating your trie file problem

DeepSpeech
#21

I tried generating trie and lm with what is given in data/lm/read.md as well and also created trie and lm but after using it. I am still getting Segmentation fault error and i dont use it on command line i get inference. so i am getting inference on default one but not on this one. i downloaded native_client.amd64.cpu.linux.tar.xz but there was also same with CUDA as well.So the error is because i am using some other generate trie or something?

#22

I can’t reply until you share more infos. And you need to answer my previous questions.

#23

This is unrelated to the LM.

#24

When I am running following command to run the model

deepspeech --model /home/sanjay/DEEPSPEECH_WORK/models/output_graph.pb
–alphabet /home/sanjay/DEEPSPEECH_WORK/models/alphabet.txt
–lm /home/sanjay/DEEPSPEECH_WORK/models/lm.binary
–trie /home/sanjay/DEEPSPEECH_WORK/models/trie
–audio /home/sanjay/maharashtra1/aaloo_cheese_sandwich_grill.wav

it is giving me output

Loading language model from files /home/sanjay/DEEPSPEECH_WORK/models/lm.binary /home/sanjay/DEEPSPEECH_WORK/models/trie
Loaded language model in 0.000131s.
Running inference.
Segmentation fault (core dumped)

and When i am running without mentioning lm and trie using command it is giving me correct inference

deepspeech --model /home/sanjay/DEEPSPEECH_WORK/models/output_graph.pb
–alphabet /home/sanjay/DEEPSPEECH_WORK/models/alphabet.txt
–audio /home/sanjay/maharashtra1/aaloo_cheese_sandwich_grill.wav

Output

Loaded model in 0.101s.
Running inference.

aaloo cheese sandwich grill
Inference took 2.745s for 3.079s audio file.

Version

TensorFlow: v1.12.0-10-ge232881
DeepSpeech: v0.4.1-0-g0e40db6

#25

I’ve asked you if you had the same behavior with the default LM. Also, what are the size of your generated files ?

#26

Just tried with default lm and trie and no it is giving correct inference. the size of my trie and lm binary is 75 bytes and 385.5 kB .
the problem is only coming when i am running model with my generated files.

#27

That’s very low. The LM at 385kB might be legit, but the 75 bytes one seems suspect.

#28

yes thank you that was the problem.The trie file was of previous vocab.I mixed it now everything is working thanks a ton!!!

1 Like