WIP: Segmentation using nnet3 for diarization and ASR #4
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
vimalmanohar
changed the title
vimalmanohar
force-pushed
the
asr_diarization_clean
branch
3 times, most recently
from
0917238
to
83cbdd6
Compare
vimalmanohar
force-pushed
the
asr_diarization_clean
branch
from
ed239a3
to
289d2b9
Compare
vimalmanohar
force-pushed
the
asr_diarization_clean
branch
from
289d2b9
to
2f5f8a1
Compare
…softmax per row, copy-matrix apply-log, matrix-add-offset, matrix-dot-product
…gments_for_data, get_utt2num_frames, get_reco2num_frames, get_reco2dur, convert_ali_to_vec, quantize_vector, convert_rttm_to_utt2spk_and_segments, get_frame_shift_from_config
…reco2file_and_channel and modify subset_data_dir.sh to add more options
and get-egs-multiple-targets
…tiple outputs in egs
…ntation_data_dir.sh
…nd testing on AMI
vimalmanohar
force-pushed
the
asr_diarization_clean
branch
from
2f5f8a1
to
8ca6a31
Compare
vimalmanohar
force-pushed
the
master
branch
2 times, most recently
from
db310c4
to
b4ef16d
Compare
vimalmanohar
force-pushed
the
master
branch
2 times, most recently
from
eff681c
to
1dabfa5
Compare
|
Aargh. It is a huge PR and it has conflicts.
I would really like from you a relatively clean PR, on top of the
'shortcut' branch if possible, that would do this as cleanly as possible
without bringing in unnecessary changes. I hope you have time for this...
Dan
…On Thu, Feb 16, 2017 at 6:31 PM, Vimal Manohar ***@***.***> wrote:
@danpovey <https://github.com/danpovey> This is the pull request. But I
have made many script changes in a different branch after this e.g. in #5
<#5> and #9
<#9>.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#4 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/ADJVuzFFOmlh0Bz9imPvAja0MqdP1e8sks5rdNxlgaJpZM4LDNuM>
.
|
vimalmanohar
pushed a commit
that referenced
this pull request
Jan 13, 2019
Added dereverberation measures, cln evaluation and updated RESULTS
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request is a place holder for all the modifications required for training nnet3 models for speech activity detection, music detection and similar tasks and using those models on test data. This includes recipes for
This PR request also contains generic tools for segmentation, nnet3 modifications for training with multi-task objectives and other generic utility scripts and binaries.