-
Couldn't load subscription status.
- Fork 1k
Train rnn with microsoft SNSD #161
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: master
Are you sure you want to change the base?
Conversation
Extending the neural network dumper to dump to a simple text file format, and adding reader functions to read a neural network description from a FILE *.
'cb' was modeled on a wide variety of signals in noise like a recording environment, making it likely a better match to what people would expect from this library than the default, which is very speech-specific for a wide variety of noise (suited to VoIP)
| dnl For some inane reason, in .so.major.minor.revision: | ||
| dnl - major = CURRENT-AGE | ||
| dnl - minor = AGE | ||
| dnl - revision = REVISION |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I am relatively sure this is not how libtool versioning works. These do not correspond to major, minor, revision, see the libtool documentation. So I believe this change is wrong.
https://github.com/microsoft/MS-SNSD
How to train rnn with microsoft SNSD datasets?