Skip to content

[aoti-et] Add Whisper large to CI #15602

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

Open
larryliu0820 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[aoti-et] Add Whisper large to CI #15602

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion .ci/scripts/test_model_cuda_e2e.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ Arguments:
Supported models:
- mistralai/Voxtral-Mini-3B-2507
- openai/whisper-small
- openai/whisper-large
- google/gemma-3-4b-it

quant_name Quantization type (required)
Expand Down Expand Up @@ -103,6 +104,18 @@ case "$HF_MODEL" in
AUDIO_FILE="output.wav"
IMAGE_PATH=""
;;
openai/whisper-large)
MODEL_NAME="whisper"
RUNNER_TARGET="whisper_runner"
RUNNER_PATH="whisper"
EXPECTED_OUTPUT="Mr. Quilter is the apostle of the middle classes"
PREPROCESSOR="whisper_preprocessor.pte"
TOKENIZER_URL="https://huggingface.co/openai/whisper-large/resolve/main" # @lint-ignore
TOKENIZER_FILE=""
AUDIO_URL=""
AUDIO_FILE="output.wav"
IMAGE_PATH=""
;;
google/gemma-3-4b-it)
MODEL_NAME="gemma3"
RUNNER_TARGET="gemma3_e2e_runner"
Expand All @@ -117,7 +130,7 @@ case "$HF_MODEL" in
;;
*)
echo "Error: Unsupported model '$HF_MODEL'"
echo "Supported models: mistralai/Voxtral-Mini-3B-2507, openai/whisper-small, google/gemma-3-4b-it"
echo "Supported models: mistralai/Voxtral-Mini-3B-2507, openai/whisper-small, openai/whisper-large, google/gemma-3-4b-it"
exit 1
;;
esac
Expand Down
4 changes: 4 additions & 0 deletions .github/workflows/cuda.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,8 @@ jobs:
name: "Voxtral-Mini-3B-2507"
- repo: "openai"
name: "whisper-small"
- repo: "openai"
name: "whisper-large"
- repo: "google"
name: "gemma-3-4b-it"
quant:
Expand Down Expand Up @@ -223,6 +225,8 @@ jobs:
name: "Voxtral-Mini-3B-2507"
- repo: "openai"
name: "whisper-small"
- repo: "openai"
name: "whisper-large"
- repo: "google"
name: "gemma-3-4b-it"
quant:
Expand Down
1 change: 1 addition & 0 deletions runtime/core/exec_aten/exec_aten.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
#include <executorch/runtime/core/portable_type/complex.h> // @manual
#include <executorch/runtime/core/portable_type/device.h> // @manual
#include <executorch/runtime/core/portable_type/half.h> // @manual
#include <executorch/runtime/core/portable_type/optional.h> // @manual
#include <executorch/runtime/core/portable_type/qint_types.h> // @manual
#include <executorch/runtime/core/portable_type/scalar.h> // @manual
#include <executorch/runtime/core/portable_type/scalar_type.h> // @manual
Expand Down
Loading