[WIP] [not-for-merge] Universal Acoustic Models

[m-wiesner]

[m-wiesner]

I checked the size of the training data per your request:

101 -- 17.8783 h 102 -- 10.0251 h 103 -- 10.3261 h 104 -- 9.9136 h 105 -- 9.91444 h 106 -- 10.6601 h 202 -- 10.8396 h 203 -- 10.5094 h 204 -- 11.7731 h 205 -- 10.2432 h 206 -- 10.3862 h 207 -- 9.83371 h 301 -- 10.3684 h 302 -- 9.92407 h 303 -- 10.2123 h 304 -- 10.651 h 305 -- 10.626 h 306 -- 10.906 h 401 -- 11.145 h 402 -- 10.6716 h 403 -- 10.4093 h total = 227.217 h

[jtrmal]

@m-wiesner , I have updated the recipe in my repository to make it run. please review changes and use git-merge or git cherry-pick to include them into your repo see: https://github.com/jtrmal/kaldi/tree/uam

[jtrmal]

(it can wait until you come back -- I can show you how to do it effectively)

[m-wiesner]

I committed a first draft of the decoding part added to the run.sh.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[stale[bot]]

This issue has been automatically closed by a bot strictly because of inactivity. This does not mean that we think that this issue is not important! If you believe it has been closed hastily, add a comment to the issue and mention @kkm000, and I'll gladly reopen it.

[stale[bot]]

This issue has been automatically marked as stale by a bot solely because it has not had recent activity. Please add any comment (simply 'ping' is enough) to prevent the issue from being closed for 60 more days if you believe it should be kept open.