From 6927c534f5b773875cbb861df33b2c4dec6bee46 Mon Sep 17 00:00:00 2001
From: Fangjun Kuang <csukuangfj@gmail.com>
Date: Tue, 9 Apr 2024 13:37:32 +0800
Subject: [PATCH] add CI for audioset

---
 .github/scripts/audioset/AT/run.sh | 34 ++++++++++++++
 .github/workflows/audioset.yml     | 74 ++++++++++++++++++++++++++++++
 2 files changed, 108 insertions(+)
 create mode 100755 .github/scripts/audioset/AT/run.sh
 create mode 100644 .github/workflows/audioset.yml

diff --git a/.github/scripts/audioset/AT/run.sh b/.github/scripts/audioset/AT/run.sh
new file mode 100755
index 000000000..ee3e102f4
--- /dev/null
+++ b/.github/scripts/audioset/AT/run.sh
@@ -0,0 +1,34 @@
+#!/usr/bin/env bash
+
+set -ex
+
+log() {
+  # This function is from espnet
+  local fname=${BASH_SOURCE[1]##*/}
+  echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
+
+cd egs/audioset/AT
+
+function test_pretrained() {
+  repo_url=https://huggingface.co/marcoyang/icefall-audio-tagging-audioset-zipformer-2024-03-12
+  repo=$(basename $repo_url)
+  GIT_LFS_SKIP_SMUDGE=1 git clone $repo_url
+  pushd $repo/exp
+  git lfs pull --include pretrained.pt
+
+  ls -lh
+
+  log "test pretrained.pt"
+
+  for w in 1.wav 2.wav 3.wav; do
+    log "test $w"
+    python3 zipformer/pretrained.py \
+      --checkpoint $repo/exp/pretrained.pt \
+      --label-dict $repo/data/class_labels_indices.csv \
+      $repo/test_wavs/$w
+  done
+
+}
+
+test_pretrained
diff --git a/.github/workflows/audioset.yml b/.github/workflows/audioset.yml
new file mode 100644
index 000000000..0d55238e5
--- /dev/null
+++ b/.github/workflows/audioset.yml
@@ -0,0 +1,74 @@
+name: audioset
+
+on:
+  push:
+    branches:
+      - master
+      - audioset-ci
+
+  pull_request:
+    branches:
+      - master
+
+  workflow_dispatch:
+
+concurrency:
+  group: audioset-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  generate_build_matrix:
+    if: github.repository_owner == 'csukuangfj' || github.repository_owner == 'k2-fsa'
+    # see https://github.com/pytorch/pytorch/pull/50633
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Generating build matrix
+        id: set-matrix
+        run: |
+          # outputting for debugging purposes
+          python ./.github/scripts/docker/generate_build_matrix.py
+          MATRIX=$(python ./.github/scripts/docker/generate_build_matrix.py)
+          echo "::set-output name=matrix::${MATRIX}"
+
+  audioset:
+    needs: generate_build_matrix
+    name: py${{ matrix.python-version }} torch${{ matrix.torch-version }} v${{ matrix.version }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        ${{ fromJson(needs.generate_build_matrix.outputs.matrix) }}
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Free space
+        shell: bash
+        run: |
+          ls -lh
+          df -h
+          rm -rf /opt/hostedtoolcache
+          df -h
+          echo "pwd: $PWD"
+          echo "github.workspace ${{ github.workspace }}"
+
+      - name: Run tests
+        uses: addnab/docker-run-action@v3
+        with:
+            image: ghcr.io/${{ github.repository_owner }}/icefall:cpu-py${{ matrix.python-version }}-torch${{ matrix.torch-version }}-v${{ matrix.version }}
+            options: |
+              --volume ${{ github.workspace }}/:/icefall
+            shell: bash
+            run: |
+              export PYTHONPATH=/icefall:$PYTHONPATH
+              cd /icefall
+              git config --global --add safe.directory /icefall
+
+              .github/scripts/audioset/AT/run.sh