Closed shiv6146 closed 5 years ago
vocab_file
is actually an alphabet, that is, a set of characters which a model can emit at each time step. There are 28 symbols in normalized LibriSpeech: 26 English characters + apostrophe + space. A CTC acoustic model has an additional CTC blank symbol. Of course, you can extend this alphabet for other datasets (see for example https://github.com/NVIDIA/OpenSeq2Seq/issues/443). trie_vocab.txt
is a set of all words in LibriSpeech which is required for building a prefix tree (trie).
@vsl9 Thanks for your insights :+1: This helps!
@blisc @borisgin What exactly does vocab_file mean? Should it be changed when different datasets are used or does it remain the same (27 symbols) irrespective of the dataset used? Does it make sense to use the
trie_vocab.txt
obtained afterdownload_lm.sh
for Librispeech to get better results?