Skip to content

fix flaky transcribe tests #12262

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

Merged
merged 3 commits into from
Mar 6, 2025
Merged

fix flaky transcribe tests #12262

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8ca4e99
fix flaky transcribe tests
sannya-singal Feb 13, 2025
515b2ca
try downloading models from artifacts
sannya-singal Mar 3, 2025
23b7094
use models from hugging face
sannya-singal Mar 5, 2025
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
3 changes: 3 additions & 0 deletions localstack-core/localstack/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,9 @@
# Artifacts endpoint
ASSETS_ENDPOINT = "https://assets.localstack.cloud"

# Hugging Face endpoint for localstack
HUGGING_FACE_ENDPOINT = "https://huggingface.co/localstack"

# host to bind to when starting the services
BIND_HOST = "0.0.0.0"

Expand Down
15 changes: 12 additions & 3 deletions localstack-core/localstack/services/transcribe/provider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
TranscriptionJobSummary,
)
from localstack.aws.connect import connect_to
from localstack.constants import HUGGING_FACE_ENDPOINT
from localstack.packages.ffmpeg import ffmpeg_package
from localstack.services.s3.utils import (
get_bucket_and_key_from_presign_url,
Expand All @@ -44,6 +45,8 @@

LOG = logging.getLogger(__name__)

VOSK_MODELS_URL = f"{HUGGING_FACE_ENDPOINT}/vosk-models/resolve/main/"

# Map of language codes to language models
LANGUAGE_MODELS = {
"en-IN": "vosk-model-small-en-in-0.4",
Expand Down Expand Up @@ -237,9 +240,15 @@ def download_model(name: str):

from vosk import MODEL_PRE_URL # noqa

download(
MODEL_PRE_URL + str(model_path.name) + ".zip", model_zip_path, verify_ssl=False
)
download_urls = [MODEL_PRE_URL, VOSK_MODELS_URL]

for url in download_urls:
try:
download(url + str(model_path.name) + ".zip", model_zip_path, verify_ssl=False)
except Exception as e:
LOG.warning("Failed to download model from %s: %s", url, e)
continue
break

LOG.debug("Extracting language model: %s", model_path.name)
with ZipFile(model_zip_path, "r") as model_ref:
Expand Down
3 changes: 0 additions & 3 deletions tests/aws/services/transcribe/test_transcribe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,6 @@ def is_transcription_done():
"$..Error..Code",
]
)
@pytest.mark.skip(reason="flaky")
def test_transcribe_happy_path(self, transcribe_create_job, snapshot, aws_client):
file_path = os.path.join(BASEDIR, "../../files/en-gb.wav")
job_name = transcribe_create_job(audio_file=file_path)
Expand Down Expand Up @@ -181,7 +180,6 @@ def is_transcription_done():
],
)
@markers.aws.needs_fixing
@pytest.mark.skip(reason="flaky")
def test_transcribe_supported_media_formats(
self, transcribe_create_job, media_file, speech, aws_client
):
Expand Down Expand Up @@ -322,7 +320,6 @@ def test_failing_start_transcription_job(self, s3_bucket, snapshot, aws_client):
(None, None), # without output bucket and output key
],
)
@pytest.mark.skip(reason="flaky")
def test_transcribe_start_job(
self,
output_bucket,
Expand Down
Loading