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.

Sign up for GitHub

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

Jump to bottom

Add dual channel support #60

Merged
merged 31 commits into from
May 19, 2023
Merged

Add dual channel support #60

merged 31 commits into from
May 19, 2023

Conversation

chainyo
Copy link
Contributor

@chainyo chainyo commented May 19, 2023 •
edited
Loading

This PR adds a lot of things:

  • Add dual channel support (an entire new pipeline to handle dual-channel audio file = one speaker on each audio side)
  • Update and simplify API endpoints models for Request and Response
  • Add a new VadService based on SileroVAD
  • Make .wav conversion for all input files if not dual_channel
  • Add new dependencies for audio manipulation (like pydub)
  • Fix alignment process
  • Update process to download audio files from URL + guessing filename and extension

chainyo and others added 24 commits May 17, 2023 08:18
add vad_filter + deps to whisper transcribe
0cfb747
add dual_channel parameter to the API
9be25e9
split process between single and dual channel
2d8db7a
add dual_channel post_process
95106d5
fix timestamps
4538350
add pydub deps
80a53a3
add audio enhancing function
e56d8a1
add docker exec command
1e4284a
fix linter and flake8
bd5261c
add sync run cmd function
daf1624
move audio split to api and utils functions
e816e65
fix asyncio stuff
9e0a1f8
remove max_initial_param
ba08067
dix DataRequest creation
011bd14
put bandpass filter to False by default
f0f1047
implement VadService
e7f5956
update dual_channel process
902fae5
fix VadService
df1aecf
this is broken
a3f8695
Made temp files for transcribed channel groups unique (in case they w…
20f59ab 
…ere interfering with one another due to parallel execution), switched temp file save method to save_audio from the VAD service, made sure seconds weren't converted to ms in dual channel
Minor adjustments for dual channel quality
c9b71d7
Added back utterance mapping for dual channel postprocessing, other s…
3ca3d89 
…mall improvements to final text output
Small improvements to final text output
453b83d
Fixing wav conversion and filepath processing for dual channel audio URL
4768a24
@chainyo chainyo linked an issue May 19, 2023 that may be closed by this pull request
Add dual-channel support #32
Closed
@chainyo chainyo added api Everything related to the API implementation audio Everything related to the audio pre or post-processing labels May 19, 2023
@chainyo chainyo marked this pull request as draft May 19, 2023 11:24
@chainyo chainyo marked this pull request as ready for review May 19, 2023 11:26
@aleksandr-smechov aleksandr-smechov merged commit 5c7d0fe into main May 19, 2023
@chainyo chainyo deleted the 32-add-dual-channel-support branch May 19, 2023 16:41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@aleksandr-smechov aleksandr-smechov aleksandr-smechov approved these changes

Assignees
No one assigned
Labels
api Everything related to the API implementation audio Everything related to the audio pre or post-processing
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Add dual-channel support
2 participants
@chainyo @aleksandr-smechov