Optimize Torchaudio Vad #3382
Closed
Optimize Torchaudio Vad #3382
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/audio/3382
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 2e2b10f: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
May 30, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 8b118af7ce854b9332ff0cf12b9a959a8c425199
KubaRad2
force-pushed
the
export-D44749359
branch
from
cbbe0a1 to
b7170b6
Compare
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
May 30, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 025afa644109714cbe8d7bfad467ee2bf2ea18bd
KubaRad2
force-pushed
the
export-D44749359
branch
from
b7170b6 to
159c7df
Compare
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
May 30, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: eb3c3ea5abb42040b9021bc22e48c916a1720d4b
KubaRad2
force-pushed
the
export-D44749359
branch
from
159c7df to
95dd40c
Compare
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
KubaRad2
force-pushed
the
export-D44749359
branch
from
95dd40c to
a88aff5
Compare
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
Jun 7, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 957340ba3d67b43d17e2605e4f24cee7b36066c3
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
Jun 7, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 44c5e69d0b56d25fb012879fc09c4305d4720be1
KubaRad2
force-pushed
the
export-D44749359
branch
from
a88aff5 to
a33d297
Compare
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
Jun 7, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: a9d2e3f0fe679ff4185b87c470a7dc172379fc0e
KubaRad2
force-pushed
the
export-D44749359
branch
from
a33d297 to
8cb8acc
Compare
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
4 similar comments
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
Jun 7, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 6b9b4839a843d506ba400455b2112db9893f4e8f
KubaRad2
force-pushed
the
export-D44749359
branch
from
b9b7b08 to
048aab4
Compare
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
Jun 7, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: b157a060521421b57e0066d9847898908a0df467
KubaRad2
force-pushed
the
export-D44749359
branch
from
8cb8acc to
b9b7b08
Compare
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
Jun 7, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 952be1ab64419bc667d55c2649c271ad2f9abd9b
KubaRad2
force-pushed
the
export-D44749359
branch
from
048aab4 to
51ce3b6
Compare
KubaRad2
added a commit
to KubaRad2/audio
that referenced
this pull request
Jun 7, 2023
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 2925bb3eecbcd0f6be8d524fdf16e51fca096d86
KubaRad2
force-pushed
the
export-D44749359
branch
from
51ce3b6 to
673405b
Compare
Summary: Pull Request resolved: pytorch#3382 The voice activity detector function was unoptimized, confusingly written, and buggy. The optimizations created here allow for the function to run roughly 17x faster. The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped. There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000] Differential Revision: D44749359 fbshipit-source-id: 21f6de116dd74807e899763af4571f85bded5095
KubaRad2
force-pushed
the
export-D44749359
branch
from
673405b to
2e2b10f
Compare
|
This pull request was exported from Phabricator. Differential Revision: D44749359 |
|
This pull request has been merged in 1e117f5. |
|
Hey @None. Some guidance:Use 'module: ops' for operations under 'torchaudio/{transforms, functional}', and ML-related components under 'torchaudio/csrc' (e.g. RNN-T loss). Things in "examples" directory:
Regarding examples in code documentations, please also use 'module: docs'. Please use 'other' tag only when you’re sure the changes are not much relevant to users, or when all other tags are not applicable. Try not to use it often, in order to minimize efforts required when we prepare release notes. When preparing release notes, please make sure 'documentation' and 'tutorials' occur as the last sub-categories under each primary category like 'new feature', 'improvements' or 'prototype'. Things related to build are by default excluded from the release note, except when it impacts users. For example: |
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.
Summary:
The voice activity detector function was unoptimized, confusingly written, and buggy.
The optimizations created here allow for the function to run roughly 17x faster.
The main optimizations were to loop over windows of audio rather than individual audio samples. Reducing the number of copies also helped.
There was an off by one error where the array slice referenced was [1: 16001] (for the default settings) instead of [0: 16000]
Differential Revision: D44749359