how to convert free-form speech audio files from anonymous speakers into
text?
I want to transcript lecture videoes where the lecture topics are from
different domain and speahers are different individuals. So, the language
model must be very large. Developing phonetic dictonary and acoustic model
is difficult and time consuming for this puopose.
is there any open souce repository for proper large language model and
phonetic dictonary and acoustic model to achieve my goal, at least for
single lecture topic domain say- computer science? Is it possible to
achieve my goal by any ASR engine ? if YES, please guide how to configure
it and how to proceed.
No comments:
Post a Comment