LibriSpeech recipe or mini_librispeech

on


I recommend for beginers to start with mini_librispeech model

LibriSpeech-larger model

https://github.com/kaldi-asr/kaldi/tree/master/egs/librispeech

 The LibriSpeech corpus is a large (1000 hour) corpus of English read speech
 derived from audiobooks in the LibriVox project, sampled at 16kHz.  The
 accents are various and not marked, but the majority are US English.  It is
 available for download for free at http://www.openslr.org/12/.  It was prepared
 as a speech recognition corpus by Vassil Panayotov.
​
 The recipe is in s5/

miniSpeech-smaller model

https://github.com/kaldi-asr/kaldi/tree/master/egs/mini_librispeech

For beginners I think it is best to start with miniSpeech, that is a small version of the above.

Note: LibriSpeech ASR model and all other needed files are provided on kaldi websites. Can be a great place to learn.

Comments

Post a Comment