Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
p1esk
on April 17, 2020
|
parent
|
context
|
favorite
| on:
Building an end-to-end Speech Recognition model in...
I opened the pdf, did ctrl+F for 'github', got zero results. Have you reproduced their "decent results"?
woodson
on April 17, 2020
[–]
ESPnet apparently already has implementations of versions of transformer transducers with RNN-T loss (though, with different network architecture). At least the paper cites results on a freely available dataset, right?
p1esk
on April 17, 2020
|
parent
[–]
Why would you not expect Google to post their code? E.g. the transformer paper had it:
https://arxiv.org/abs/1706.03762
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
