Keyerror in self str to label string of deepspeech util text py when training own model

[JRMeyer]

>>> mark2
[January 22, 2018, 8:32am]

Hi!

I am training my own model on Ubuntu as described in TUTORIAL : How I
trained a specific french model to control my
robot

## However, I get an error:

## WARNING: libdeepspeech failed to load, resorting to deprecated code Refer to README.md for instructions on installing libdeepspeech

Exception in thread Thread-3: slash
Traceback (most recent call last): slash
File '/usr/lib/python2.7/threading.py', line 801, in
slash _ slash _bootstrap_inner slash
self.run() slash
File '/usr/lib/python2.7/threading.py', line 754, in run slash
self. slash _ slash _target( slash *self. slash _ slash _args, slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org foo foo~ html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts sorted-deepspeech-posts~ slash *self. slash _ slash _kwargs) slash
File '/home/ubuntu/DeepSpeech/util/feeding.py', line 148, in
slash _populate_batch_queue slash
target = text_to_char_array(transcript, self. slash _alphabet) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 40, in
text_to_char_array slash
return np.asarray( slash [alphabet.label_from_string© for c in original slash ]) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 30, in
label_from_string slash
return self. slash _str_to_label slash [string slash ] slash
KeyError: u'k'

Exception in thread Thread-4: slash
Traceback (most recent call last): slash
File '/usr/lib/python2.7/threading.py', line 801, in
slash _ slash _bootstrap_inner slash
self.run() slash
File '/usr/lib/python2.7/threading.py', line 754, in run slash
self. slash _ slash _target( slash *self. slash _ slash _args, slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org foo foo~ html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts sorted-deepspeech-posts~ slash *self. slash _ slash _kwargs) slash
File '/home/ubuntu/DeepSpeech/util/feeding.py', line 148, in
slash _populate_batch_queue slash
target = text_to_char_array(transcript, self. slash _alphabet) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 40, in
text_to_char_array slash
return np.asarray( slash [alphabet.label_from_string© for c in original slash ]) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 30, in
label_from_string slash
return self. slash _str_to_label slash [string slash ] slash
KeyError: u'l'

Exception in thread Thread-5: slash
Traceback (most recent call last): slash
File '/usr/lib/python2.7/threading.py', line 801, in
slash _ slash _bootstrap_inner slash
self.run() slash
File '/usr/lib/python2.7/threading.py', line 754, in run slash
self. slash _ slash _target( slash *self. slash _ slash _args, slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org foo foo~ html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts sorted-deepspeech-posts~ slash *self. slash _ slash _kwargs) slash
File '/home/ubuntu/DeepSpeech/util/feeding.py', line 148, in
slash _populate_batch_queue slash
target = text_to_char_array(transcript, self. slash _alphabet) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 40, in
text_to_char_array slash
return np.asarray( slash [alphabet.label_from_string© for c in original slash ]) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 30, in
label_from_string slash
return self. slash _str_to_label slash [string slash ] slash
KeyError: u't'

Exception in thread Thread-6: slash
Traceback (most recent call last): slash
File '/usr/lib/python2.7/threading.py', line 801, in
slash _ slash _bootstrap_inner slash
self.run() slash
File '/usr/lib/python2.7/threading.py', line 754, in run slash
self. slash _ slash _target( slash *self. slash _ slash _args, slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org foo foo~ html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts sorted-deepspeech-posts~ slash *self. slash _ slash _kwargs) slash
File '/home/ubuntu/DeepSpeech/util/feeding.py', line 148, in
slash _populate_batch_queue slash
target = text_to_char_array(transcript, self. slash _alphabet) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 40, in
text_to_char_array slash
return np.asarray( slash [alphabet.label_from_string© for c in original slash ]) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 30, in
label_from_string slash
return self. slash _str_to_label slash [string slash ] slash
KeyError: u'o' slash
Exception in thread Thread-7: slash
Traceback (most recent call last): slash
File '/usr/lib/python2.7/threading.py', line 801, in
slash _ slash _bootstrap_inner slash
self.run() slash
File '/usr/lib/python2.7/threading.py', line 754, in run slash
self. slash _ slash _target( slash *self. slash _ slash _args, slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org foo foo~ html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts sorted-deepspeech-posts~ slash *self. slash _ slash _kwargs) slash
File '/home/ubuntu/DeepSpeech/util/feeding.py', line 148, in
slash _populate_batch_queue slash
target = text_to_char_array(transcript, self. slash _alphabet) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 40, in
text_to_char_array slash
return np.asarray( slash [alphabet.label_from_string© for c in original slash ]) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 30, in
label_from_string slash
return self. slash _str_to_label slash [string slash ] slash
KeyError: u't'

Exception in thread Thread-8: slash
Traceback (most recent call last): slash
File '/usr/lib/python2.7/threading.py', line 801, in
slash _ slash _bootstrap_inner slash
self.run() slash
File '/usr/lib/python2.7/threading.py', line 754, in run slash
self. slash _ slash _target( slash *self. slash _ slash _args, slash DEEPSPEECH.cdx deepspeech.commands DEEPSPEECH.pages DEEPSPEECH.warc.gz discourse.mozilla.org foo foo~ html-to-markdown.sh shell-conver-html-to-split-posts.sh sorted-deepspeech-posts sorted-deepspeech-posts~ slash *self. slash _ slash _kwargs) slash
File '/home/ubuntu/DeepSpeech/util/feeding.py', line 148, in
slash _populate_batch_queue slash
target = text_to_char_array(transcript, self. slash _alphabet) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 40, in
text_to_char_array slash
return np.asarray( slash [alphabet.label_from_string© for c in original slash ]) slash
File '/home/ubuntu/DeepSpeech/util/text.py', line 30, in
label_from_string slash
return self. slash _str_to_label slash [string slash ] slash
KeyError: u't'

If I understood correctly, some characters are not present in the
dirctionary. But I don't understand why as 'o', 't', 'l' and other it
complains about are present in alphabet.txt.

Any ideas where it could go wrong?



[Training Chinese model



[DEEPSPEECH traning problem data feeding

[This is an archived TTS discussion thread from discourse.mozilla.org/t/keyerror-in-self-str-to-label-string-of-deepspeech-util-text-py-when-training-own-model]

[JRMeyer]

>>> lissyx
[January 22, 2018, 9:54am]

I do remember hitting and debugging the same issue already in the past,
and the trick was that the characters were present in alphabet.txt but
under different UTF-8 codes than in the transcript. So, don't trust
your eyes.

[Archived Post]

[JRMeyer]

>>> mark2
[January 22, 2018, 12:12pm]

Yeah, you are right. It was the issue!

[Archived Post]