Granary large-scale speech processing pipeline #5

	name: Granary pipeline E2E test

	on:
	pull_request:
	branches: [ "main" ]

	# Allows you to run this workflow manually from the Actions tab
	workflow_dispatch:

	permissions:
	contents: read

	jobs:
	granary-e2e-test:
	runs-on: ubuntu-latest

	steps:
	- uses: actions/checkout@v3
	- name: Set up Python 3.10
	uses: actions/setup-python@v3
	with:
	python-version: "3.10"
	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -r requirements/main.txt
	pip install -r requirements/tests.txt
	sudo apt-get update
	sudo apt-get install -y libsndfile1 ffmpeg sox libsox-fmt-mp3
	pip install nemo-toolkit[asr]==2.2.1
	pip install fasttext
	python -m pip cache purge

	- name: Run Granary E2E test
	env:
	AWS_SECRET_KEY: ${{ secrets.AWS_SECRET_KEY }}
	AWS_ACCESS_KEY: ${{ secrets.AWS_ACCESS_KEY }}
	CLEAN_UP_TMP_PATH: 1
	USE_THREADING_BACKEND: 1
	run: \|
	python -m pytest tests/test_granary_pipeline_end_to_end.py tests/test_data_to_data.py

Provide feedback