[aoti-et] Add an ASR runner and an Whisper example to showcase how to use it #15486
Conversation
This file contains hidden or 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
larryliu0820
requested review from
jackzhxng,
kirklandsign and
lucylq
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15486
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 New Failure, 17 Pending, 1 Unrelated FailureAs of commit 23b7c15 with merge base cc72b35 ( NEW FAILURE - The following job has failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
Gasoonjia
reviewed
Oct 31, 2025
There was a problem hiding this comment.
LGTM on my side. I will let @jackzhxng give the stamp about asr_runner.
use it **Key Changes:** * Create new ASR runner extension in `extension/asr/runner/` with reusable runner components (runner.h/cpp) * Update CMake configuration files to support ASR runner builds (executorch-config.cmake, default.cmake, llm.cmake) * Add new Whisper model example in `examples/models/whisper/` with CMake build, README, and main.cpp runner * Bump optimum-executorch commit pin for Whisper support * Update CUDA CI workflow for testing This change enables automatic speech recognition (ASR) capabilities in ExecuTorch with Whisper as the first supported model, following a similar pattern to the existing LLM runner infrastructure.
larryliu0820
force-pushed
the
asr_runner
branch
from
2484896 to
f348cee
Compare
jackzhxng
approved these changes
Nov 3, 2025
mergennachin
requested changes
Nov 3, 2025
| #include <executorch/runtime/core/result.h> | ||
| #include <pytorch/tokenizers/tokenizer.h> | ||
|
|
||
| namespace executorch::extension::asr { |
There was a problem hiding this comment.
Once this lands, we can renew this PR and add language bindings
Comment on lines
+76
to
+79
| if(EXECUTORCH_BUILD_METAL) | ||
| list(APPEND _link_libraries metal_backend) | ||
| executorch_target_link_options_shared_lib(metal_backend) | ||
| endif() |
There was a problem hiding this comment.
Is metal supported?
jackzhxng
reviewed
Nov 3, 2025
mergennachin
reviewed
Nov 3, 2025
mergennachin
reviewed
Nov 3, 2025
mergennachin
reviewed
Nov 3, 2025
mergennachin
reviewed
Nov 3, 2025
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.
Key Changes:
extension/asr/runner/with reusable runner components (runner.h/cpp)examples/models/whisper/with CMake build, README, and main.cpp runnerThis change enables automatic speech recognition (ASR) capabilities in ExecuTorch with Whisper as the first supported model, following a similar pattern to the existing LLM runner infrastructure.