-
Notifications
You must be signed in to change notification settings - Fork 621
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
Implement Row Convolution in PyTorch #46
Comments
I wanted to work on this if you do not mind? |
Go for it @EgorLakomkin! Let me know if you run into issues etc |
@EgorLakomkin you may find this helpful: PaddlePaddle/Paddle#2373 |
Make any headway here @EgorLakomkin? |
Thx for the links @ryanleary ! I will push the vanilla implementation this week |
What is a row convolution? |
@EgorLakomkin did you have any luck with this? |
bump!? |
1 similar comment
bump!? |
Did you see this? Is it different from the DS2's row conv layer? |
It is! Thanks @jinserk that will be super useful. |
Sorry for late reply, recently been very busy. I am experimenting with convolutional-only acoustic models (like wav2letter) and I was thinking if it would be interesting to include them in this repo though it is not related to deepspeech? |
Bump! I implemented wav2letter-like architecture recently and it works quite good, but faster than rnn-based models. Do you think it could be a good addition to this repo? |
Make it a branch? I'll more than happily take it as a new branch :) |
It would be cool to eventually support different model types within this repo if the model loading/options etc can be handled in a robust way. There is a lot of boilerplate code here that would be necessary for any speech system, so certainly good to reuse it. |
Amazing!!!
Em 12 de out de 2017 4:09 PM, "Ryan Leary" <notifications@github.com>
escreveu:
… It would be cool to eventually support different model types within this
repo if the model loading/options etc can be handled in a robust way. There
is a lot of boilerplate code here that would be necessary for any speech
system, so certainly good to reuse it.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#46 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AOTmHN3VnbyP6drvQMSYwarEjeHO2MBrks5srmP7gaJpZM4NQ8vu>
.
|
Added in #180 |
This will give us the ability to do a real time model, being able to predict just using forward only RNNs.
The text was updated successfully, but these errors were encountered: