support/optimize ASR on HPU #280
Merged
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
Signed-off-by: Spycsh <[email protected]>
for more information, see https://pre-commit.ci
chensuyue
approved these changes
Jun 12, 2024
hshen14
approved these changes
Jun 12, 2024
Spycsh
added a commit
to Spycsh/GenAIExamples
that referenced
this pull request
Jun 19, 2024
* optimize asr on hpu Signed-off-by: Spycsh <[email protected]>
yogeshmpandey
pushed a commit
to hteeyeoh/GenAIExamples
that referenced
this pull request
Aug 12, 2024
* optimize asr on hpu Signed-off-by: Spycsh <[email protected]>
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Outdated suggestions cannot be applied.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.
Description
In this PR Whisper ASR inference is enabled on HPU, and at the same time optimized with one warmup with a long enough audio. (<The Whisper short-form case 30s limit). After this warmup, future shorter generation should follow the same subset of cached HPU graph and be fast. The e2e perf gain HPU compared to CPU can be up to roughly 2~3x.
Language is updated to be required as explicitly specified: (e.g. "english", "chinese"). Check the Whisper compatible language list. The default language is "english". We deprecate the auto language detection (where
AudioSpeechRecognition.languageis None) until #1049 is considered to be handled. It is not a must except for special usage. The default language is "english".Issues
List the issue or RFC link this PR is working on. If there is no such link, please mark it as
n/a.Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
None
Tests
None