Skip to content
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

Add left biphone recipe for swbd #774

Merged
merged 2 commits into from
May 16, 2016

Conversation

naxingyu
Copy link
Contributor

This is a WIP PR to track the progress in left biphone chain modeling, as requested by #766 . The results will be updated in the script instead of RESULT because it is WIP.

@naxingyu naxingyu force-pushed the chain-left-biphone branch 2 times, most recently from f967c2e to 27c8531 Compare May 11, 2016 09:49
train_stage=-10
get_egs_stage=-10
speed_perturb=true
dir=exp/chain/tdnn_7b # Note: _sp will get added to this if $speed_perturb == true.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

tdnn_7b --> tdnn_7d

@vijayaditya
Copy link
Contributor

I will merge once the conflicts have been resolved.

@naxingyu
Copy link
Contributor Author

Thanks Vij. There should be no conflict. Maybe it is the WIP tag that
disable the merging.
The '.nodelete' line of script came from run_tdnn_7b.sh. I'll deleted
it, but I think there should be a cleanup in the swbd chain recipe dir,
since it is quite noisy AS IS.

在 2016/5/13 10:24, Vijayaditya Peddinti 写道:

I will merge once the conflicts have been resolved.


You are receiving this because you authored the thread.
Reply to this email directly or view it on GitHub
#774 (comment)

@naxingyu naxingyu changed the title WIP: add left biphone recipe for swbd Add left biphone recipe for swbd May 13, 2016
@naxingyu
Copy link
Contributor Author

Updated and WIP removed. Ready to merge.

在 2016/5/13 10:24, Vijayaditya Peddinti 写道:

I will merge once the conflicts have been resolved.


You are receiving this because you authored the thread.
Reply to this email directly or view it on GitHub
#774 (comment)

@vijayaditya
Copy link
Contributor

Sorry @naxingyu I failed to merge this last time you cleared the conflicts. Could you do a rebase your branch as it is currently out-of-date ? I will merge immediately now.

@naxingyu
Copy link
Contributor Author

I could, but it's strange that I don't see a conflict message on
Github... The files I committed are not conflicting with any other PR.

在 2016/5/16 10:02, Vijayaditya Peddinti 写道:

Sorry @naxingyu https://github.com/naxingyu I failed to merge this
last time you cleared the conflicts. Could you do a rebase your branch
as it is currently out-of-date ? I will merge immediately now.


You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#774 (comment)

@vijayaditya
Copy link
Contributor

There are no conflicts, github is just saying that your branch is stale
compared to the master. A rebase would solve this issue.

--Vijay

On Mon, May 16, 2016 at 7:43 AM, Xingyu Na notifications@github.com wrote:

I could, but it's strange that I don't see a conflict message on
Github... The files I committed are not conflicting with any other PR.

在 2016/5/16 10:02, Vijayaditya Peddinti 写道:

Sorry @naxingyu https://github.com/naxingyu I failed to merge this
last time you cleared the conflicts. Could you do a rebase your branch
as it is currently out-of-date ? I will merge immediately now.


You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you commented.
Reply to this email directly or view it on GitHub
#774 (comment)

@naxingyu
Copy link
Contributor Author

I see. Is it ok now?

Xingyu

在 2016/5/16 10:18, Vijayaditya Peddinti 写道:

There are no conflicts, github is just saying that your branch is stale
compared to the master. A rebase would solve this issue.

--Vijay

On Mon, May 16, 2016 at 7:43 AM, Xingyu Na notifications@github.com
wrote:

I could, but it's strange that I don't see a conflict message on
Github... The files I committed are not conflicting with any other PR.

在 2016/5/16 10:02, Vijayaditya Peddinti 写道:

Sorry @naxingyu https://github.com/naxingyu I failed to merge this
last time you cleared the conflicts. Could you do a rebase your branch
as it is currently out-of-date ? I will merge immediately now.


You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you commented.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#774 (comment)

@danpovey
Copy link
Contributor

I think it's OK. It's because yenda made that github configuration
change. As long as it's only changes in scripts, it's always safe to merge
such things.

On Sun, May 15, 2016 at 10:18 PM, Vijayaditya Peddinti <
notifications@github.com> wrote:

There are no conflicts, github is just saying that your branch is stale
compared to the master. A rebase would solve this issue.

--Vijay

On Mon, May 16, 2016 at 7:43 AM, Xingyu Na notifications@github.com
wrote:

I could, but it's strange that I don't see a conflict message on
Github... The files I committed are not conflicting with any other PR.

在 2016/5/16 10:02, Vijayaditya Peddinti 写道:

Sorry @naxingyu https://github.com/naxingyu I failed to merge this
last time you cleared the conflicts. Could you do a rebase your branch
as it is currently out-of-date ? I will merge immediately now.


You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you commented.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub
#774 (comment)

@vijayaditya vijayaditya merged commit 80d6d07 into kaldi-asr:master May 16, 2016
@vijayaditya
Copy link
Contributor

Yep. Thanks for making the change. I merged the PR.

On Mon, May 16, 2016 at 7:50 AM, Xingyu Na notifications@github.com wrote:

I see. Is it ok now?

Xingyu

在 2016/5/16 10:18, Vijayaditya Peddinti 写道:

There are no conflicts, github is just saying that your branch is stale
compared to the master. A rebase would solve this issue.

--Vijay

On Mon, May 16, 2016 at 7:43 AM, Xingyu Na notifications@github.com
wrote:

I could, but it's strange that I don't see a conflict message on
Github... The files I committed are not conflicting with any other PR.

在 2016/5/16 10:02, Vijayaditya Peddinti 写道:

Sorry @naxingyu https://github.com/naxingyu I failed to merge this
last time you cleared the conflicts. Could you do a rebase your
branch
as it is currently out-of-date ? I will merge immediately now.


You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you commented.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub
#774 (comment)


You are receiving this because you commented.
Reply to this email directly or view it on GitHub
#774 (comment)

@naxingyu naxingyu deleted the chain-left-biphone branch May 16, 2016 02:27
@danpovey
Copy link
Contributor

danpovey commented Aug 5, 2016

@naxingyu , I notice in the RESULTS file in swbd/s5c there is a very out-of-date, suboptimal chain system listed there. Currently I think this 7d is the recommended system, but I don't have access to it because you ran it. Can you please remove the current chain+tdnn system in the RESULTS file and replace it with the corresponding results from this system?

@naxingyu
Copy link
Contributor Author

naxingyu commented Aug 5, 2016

OK

在 2016/8/5 8:04, Daniel Povey 写道:

@naxingyu https://github.com/naxingyu , I notice in the RESULTS file
in swbd/s5c there is a very out-of-date, suboptimal chain system
listed there. Currently I think this 7d is the recommended system, but
I don't have access to it because you ran it. Can you please remove
the current chain+tdnn system in the RESULTS file and replace it with
the corresponding results from this system?


You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
#774 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/ADKpxMqOebk489rF3BjQxQXOUnIScPA3ks5qcn4GgaJpZM4Ib3YV.

@naxingyu naxingyu mentioned this pull request Aug 5, 2016
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants