Issue in decoding

[JRMeyer]

>>> noor_e slash _emaan11
[May 13, 2019, 9:44am]

After training, I got this error which is even after validation. slash
Pre-processing of the test set was also done. But It gave me errors
while decoding. slash
It also computed the acoustic model.

Traceback (most recent call last): slash
File 'DeepSpeech.py', line 942, in slash
tf.app.run(main) slash
File
'/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/app.py',
line 125, in run slash
slash _sys.exit(main(argv)) slash
File 'DeepSpeech.py', line 898, in main slash
test() slash
File 'DeepSpeech.py', line 659, in test slash
evaluate.evaluate(test_data, graph) slash
File '/home/cle-dl-1/DeepSpeech/DeepSpeech-0.4.1/evaluate.py', line 179,
in evaluate slash
num_processes=num_processes, scorer=scorer) slash
File '/usr/local/lib/python3.6/dist-packages/ds_ctcdecoder/init.py',
line 102, in ctc_beam_search_decoder_batch slash
for beam_results in batch_beam_results slash
File '/usr/local/lib/python3.6/dist-packages/ds_ctcdecoder/init.py',
line 102, in slash
for beam_results in batch_beam_results slash
File '/usr/local/lib/python3.6/dist-packages/ds_ctcdecoder/init.py',
line 101, in slash
slash [(res.probability, alphabet.decode(res.tokens)) for res in
beam_results slash ] slash
File '/home/cle-dl-1/DeepSpeech/DeepSpeech-0.4.1/util/text.py', line 50,
in decode slash
res += self.string_from_label(label) slash
File '/home/cle-dl-1/DeepSpeech/DeepSpeech-0.4.1/util/text.py', line 29,
in string_from_label slash
return self. slash _label_to_str slash [label slash ] slash
IndexError: list index out of range

388

[This is an archived TTS discussion thread from discourse.mozilla.org/t/issue-in-decoding]

[JRMeyer]

>>> lissyx
[May 13, 2019, 12:43pm]



> return self. slash _label_to_str slash [label slash ] slash
> IndexError: list index out of range

This is mismatching alphabet file: some of your data contains characters
not in your alphabet file.

[Archived Post]

[JRMeyer]

>>> noor_e slash _emaan11
[May 15, 2019, 4:34am]

Okay. Thank you! It has been resolved. But the problem now is, it
doesn't give me any output in decoding. I trained on almost 100 hours of
data and longest transcription it has is almost 12 seconds. slash
I got the model, things work fine but it always giving me the blank
result. Why is it so ?

[Archived Post]

[JRMeyer]

>>> lissyx
[May 15, 2019, 7:18am]

There could a lot of reasons, without more details on your training
setup it's hard to tell anything ...

[Archived Post]

[JRMeyer]

>>> Sushantmkarande
[May 21, 2019, 2:37pm]

i am getting
the same error can you tell me how did your problem resolved slash
i did not find any character in dataset which is not in alphabet,

[Archived Post]

[JRMeyer]

>>> noor_e slash _emaan11
[May 22, 2019, 5:32am]

Check your flags.py, alphabet.txt file, put all the characters from
train, test and dev even they are replicating. slash
This error occured randomly with me. I couldn't specify one reason for
it. slash
try with next iteration after checking flag.py, hopefully, It will
resolve.

[Archived Post]

[JRMeyer]

>>> Sushantmkarande
[May 23, 2019, 6:25am]

THANKS... my problem is solved, there was no ' character in my
alphabet.txt.

[Archived Post]