-
Notifications
You must be signed in to change notification settings - Fork 235
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
Adds audio querying to MultimodalQ&A Example #1225
Adds audio querying to MultimodalQ&A Example #1225
Conversation
Signed-off-by: okhleif-IL <omar.khleif@intel.com> * validated, updated tests Signed-off-by: okhleif-IL <omar.khleif@intel.com> * added one more curl test for audio Signed-off-by: okhleif-IL <omar.khleif@intel.com> * fixed typo Signed-off-by: okhleif-IL <omar.khleif@intel.com> * reverted git clone command Signed-off-by: okhleif-IL <omar.khleif@intel.com> * added ASR test Signed-off-by: okhleif-IL <omar.khleif@intel.com> * fixed command with backslashes Signed-off-by: okhleif-IL <omar.khleif@intel.com> --------- Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com> Signed-off-by: okhleif-IL <omar.khleif@intel.com> Signed-off-by: dmsuehir <dina.s.jones@intel.com>
* MMQnA doc update correcting ASR and whisper image names Signed-off-by: dmsuehir <dina.s.jones@intel.com> * Add image tags Signed-off-by: dmsuehir <dina.s.jones@intel.com> --------- Signed-off-by: dmsuehir <dina.s.jones@intel.com>
* Enabled audio query functionality in the MultimodalQnA UI Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com>
Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com>
Temporarily redirect clones for tests
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM but don't merge please unless the branch is changed to point to main
again.
* Add services to tests and correct small text error Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com> * Revert unintended changes Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com> --------- Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com>
Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Holding off on this PR until opea-project/GenAIComps#974 is merged.
Fixed build.yaml inconsistency
Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com>
Update repo clones for MultimodalQnA E2E tests
* Moved gateway changes to multimodalqna.py Signed-off-by: okhleif-IL <omar.khleif@intel.com> * reverted port changes Signed-off-by: okhleif-IL <omar.khleif@intel.com> * addressed review comments Signed-off-by: okhleif-IL <omar.khleif@intel.com> * reverted print statement Signed-off-by: okhleif-IL <omar.khleif@intel.com> --------- Signed-off-by: okhleif-IL <omar.khleif@intel.com>
* Moved gateway changes to multimodalqna.py Signed-off-by: okhleif-IL <omar.khleif@intel.com> * reverted port changes Signed-off-by: okhleif-IL <omar.khleif@intel.com> * addressed review comments Signed-off-by: okhleif-IL <omar.khleif@intel.com> * reverted print statement Signed-off-by: okhleif-IL <omar.khleif@intel.com> * removed proxies Signed-off-by: okhleif-IL <omar.khleif@intel.com> --------- Signed-off-by: okhleif-IL <omar.khleif@intel.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
Signed-off-by: Melanie Buehler <melanie.h.buehler@intel.com> Signed-off-by: okhleif-IL <omar.khleif@intel.com> Signed-off-by: dmsuehir <dina.s.jones@intel.com> Co-authored-by: Omar Khleif <omar.khleif@intel.com> Co-authored-by: Dina Suehiro Jones <dina.s.jones@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Abolfazl Shahbazi <12436063+ashahba@users.noreply.github.com> Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>
Description
Adds the option to speak into the browser microphone or upload an audio file to the main query tab. The speech audio is POSTed as a base64 string to the MultimodalQnA gateway where it is transcribed to text by the ASR whisper service and then passed on to the LVM service.
Note: This PR has been updated so that the changes to the megaservice are included in this repo in
multimodalqna.py
, so a corresponding PR to GenAIComps is not needed.Issues
This is a part of the MultimodalQnA Image & Audio Enhancements RFC
Type of change
Dependencies
N/A
Tests
New tests were added to the example's
README.md
,test_compose_on_xeon.sh
, andtest_compose_on_gaudi.sh
.