robmsmt / KerasDeepSpeech

A Keras CTC implementation of Baidu's DeepSpeech for model experimentation
GNU Affero General Public License v3.0
242 stars 79 forks source link

Padding character: #27 or 28? #16

Open alexdiment opened 5 years ago

alexdiment commented 5 years ago

https://github.com/robmsmt/KerasDeepSpeech/blob/553638821c996cb6049e34185babacdb8f00c215/generator.py#L215

In generator.py, get_intseq(), the padding is done with character 27. In the char map, it stands for an apostrophe, not the extra 28th padding character. In utils.py, int_to_text_sequence, a character 28 is mentioned as the one for padding. Is that intended?