From 010c311fd6d4f12a5140d060cfcca263a4cf1a2a Mon Sep 17 00:00:00 2001
From: Fangjun Kuang <csukuangfj@gmail.com>
Date: Mon, 25 Dec 2023 13:47:02 +0800
Subject: [PATCH] Use cpu docker to run yesno

---
 .../{docker => librispeech/ASR}/run.sh        |  11 +-
 .github/scripts/yesno/ASR/run.sh              |  84 ++++++++
 .github/workflows/run-yesno-recipe.yml        | 182 ++++--------------
 .github/workflows/train-librispeech.yml       |   6 +-
 4 files changed, 131 insertions(+), 152 deletions(-)
 rename .github/scripts/{docker => librispeech/ASR}/run.sh (86%)
 create mode 100755 .github/scripts/yesno/ASR/run.sh

diff --git a/.github/scripts/docker/run.sh b/.github/scripts/librispeech/ASR/run.sh
similarity index 86%
rename from .github/scripts/docker/run.sh
rename to .github/scripts/librispeech/ASR/run.sh
index aeb80b330..2fdfc6e32 100755
--- a/.github/scripts/docker/run.sh
+++ b/.github/scripts/librispeech/ASR/run.sh
@@ -1,11 +1,10 @@
 #!/usr/bin/env bash
-set -ex
 
-cd /icefall
-export PYTHONPATH=/icefall:$PYTHONPATH
-python3 -c "import torch; print(torch.__file__)"
-python3 -c "import torchaudio; print(torchaudio.__version__)"
-python3 -c "import icefall; print(icefall.__file__)"
+log() {
+  # This function is from espnet
+  local fname=${BASH_SOURCE[1]##*/}
+  echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
+}
 
 cd egs/librispeech/ASR
 
diff --git a/.github/scripts/yesno/ASR/run.sh b/.github/scripts/yesno/ASR/run.sh
new file mode 100755
index 000000000..c3f445d8c
--- /dev/null
+++ b/.github/scripts/yesno/ASR/run.sh
@@ -0,0 +1,84 @@
+#!/usr/bin/env bash
+
+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/yesno/ASR
+
+log "data preparation"
+./prepare.sh
+
+log "training"
+python3 ./tdnn/train.py
+
+log "decoding"
+python3 ./tdnn/decode.py
+
+log "export to pretrained.pt"
+
+python3 ./tdnn/export.py --epoch 14 --avg 2
+
+python3 ./tdnn/pretrained.py \
+  --checkpoint ./tdnn/exp/pretrained.pt \
+  --HLG ./data/lang_phone/HLG.pt \
+  --words-file ./data/lang_phone/words.txt \
+  download/waves_yesno/0_0_0_1_0_0_0_1.wav \
+  download/waves_yesno/0_0_1_0_0_0_1_0.wav
+
+log "Test exporting to torchscript"
+python3 ./tdnn/export.py --epoch 14 --avg 2 --jit 1
+
+python3 ./tdnn/jit_pretrained.py \
+  --nn-model ./tdnn/exp/cpu_jit.pt \
+  --HLG ./data/lang_phone/HLG.pt \
+  --words-file ./data/lang_phone/words.txt \
+  download/waves_yesno/0_0_0_1_0_0_0_1.wav \
+  download/waves_yesno/0_0_1_0_0_0_1_0.wav
+
+log "Test exporting to onnx"
+python3 ./tdnn/export_onnx.py --epoch 14 --avg 2
+
+log "Test float32 model"
+python3 ./tdnn/onnx_pretrained.py \
+  --nn-model ./tdnn/exp/model-epoch-14-avg-2.onnx \
+  --HLG ./data/lang_phone/HLG.pt \
+  --words-file ./data/lang_phone/words.txt \
+  download/waves_yesno/0_0_0_1_0_0_0_1.wav \
+  download/waves_yesno/0_0_1_0_0_0_1_0.wav
+
+log "Test int8 model"
+python3 ./tdnn/onnx_pretrained.py \
+  --nn-model ./tdnn/exp/model-epoch-14-avg-2.int8.onnx \
+  --HLG ./data/lang_phone/HLG.pt \
+  --words-file ./data/lang_phone/words.txt \
+  download/waves_yesno/0_0_0_1_0_0_0_1.wav \
+  download/waves_yesno/0_0_1_0_0_0_1_0.wav
+
+log "Test decoding with H"
+python3 ./tdnn/export.py --epoch 14 --avg 2 --jit 1
+
+python3 ./tdnn/jit_pretrained_decode_with_H.py \
+    --nn-model ./tdnn/exp/cpu_jit.pt \
+    --H ./data/lang_phone/H.fst \
+    --tokens ./data/lang_phone/tokens.txt \
+    ./download/waves_yesno/0_0_0_1_0_0_0_1.wav \
+    ./download/waves_yesno/0_0_1_0_0_0_1_0.wav \
+    ./download/waves_yesno/0_0_1_0_0_1_1_1.wav
+
+log "Test decoding with HL"
+python3 ./tdnn/export.py --epoch 14 --avg 2 --jit 1
+
+python3 ./tdnn/jit_pretrained_decode_with_HL.py \
+    --nn-model ./tdnn/exp/cpu_jit.pt \
+    --HL ./data/lang_phone/HL.fst \
+    --words ./data/lang_phone/words.txt \
+    ./download/waves_yesno/0_0_0_1_0_0_0_1.wav \
+    ./download/waves_yesno/0_0_1_0_0_0_1_0.wav \
+    ./download/waves_yesno/0_0_1_0_0_1_1_1.wav
+
+log "Show generated files"
+ls -lh tdnn/exp
+ls -lh data/lang_phone
diff --git a/.github/workflows/run-yesno-recipe.yml b/.github/workflows/run-yesno-recipe.yml
index 9ac848535..a99811815 100644
--- a/.github/workflows/run-yesno-recipe.yml
+++ b/.github/workflows/run-yesno-recipe.yml
@@ -20,166 +20,60 @@ on:
   push:
     branches:
       - master
+      - refactor-ci
+
   pull_request:
     branches:
       - master
 
+  workflow_dispatch:
+
 concurrency:
   group: run-yesno-recipe-${{ 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}"
   run-yesno-recipe:
-    runs-on: ${{ matrix.os }}
+    needs: generate_build_matrix
+    name: py${{ matrix.python-version }} torch${{ matrix.torch-version }} v${{ matrix.version }}
+    runs-on: ubuntu-latest
     strategy:
-      matrix:
-        # os: [ubuntu-latest, macos-10.15]
-        # TODO: enable macOS for CPU testing
-        os: [ubuntu-latest]
-        python-version: [3.8]
       fail-fast: false
+      matrix:
+        ${{ fromJson(needs.generate_build_matrix.outputs.matrix) }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
-      - name: Setup Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+      - name: Run the yesno recipe
+        uses: addnab/docker-run-action@v3
         with:
-          python-version: ${{ matrix.python-version }}
-          cache: 'pip'
-          cache-dependency-path: '**/requirements-ci.txt'
+            image: ghcr.io/${{ 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
 
-      - name: Install libnsdfile and libsox
-        if: startsWith(matrix.os, 'ubuntu')
-        run: |
-          sudo apt update
-          sudo apt install -q -y libsndfile1-dev libsndfile1 ffmpeg
-          sudo apt install -q -y --fix-missing sox libsox-dev libsox-fmt-all
-
-      - name: Install Python dependencies
-        run: |
-          grep -v '^#' ./requirements-ci.txt  | xargs -n 1 -L 1 pip install
-          pip uninstall -y protobuf
-          pip install --no-binary protobuf protobuf==3.20.*
-
-          pip install --no-deps --force-reinstall k2==1.24.4.dev20231021+cpu.torch1.13.1 -f https://k2-fsa.github.io/k2/cpu.html
-          pip install kaldifeat==1.25.1.dev20231022+cpu.torch1.13.1 -f https://csukuangfj.github.io/kaldifeat/cpu.html
-
-      - name: Run yesno recipe
-        shell: bash
-        working-directory: ${{github.workspace}}
-        run: |
-          export PYTHONPATH=$PWD:$PYTHONPATH
-          echo $PYTHONPATH
-
-          cd egs/yesno/ASR
-          ./prepare.sh
-          python3 ./tdnn/train.py
-          python3 ./tdnn/decode.py
-
-      - name: Test exporting to pretrained.pt
-        shell: bash
-        working-directory: ${{github.workspace}}
-        run: |
-          export PYTHONPATH=$PWD:$PYTHONPATH
-          echo $PYTHONPATH
-
-          cd egs/yesno/ASR
-          python3 ./tdnn/export.py --epoch 14 --avg 2
-
-          python3 ./tdnn/pretrained.py \
-            --checkpoint ./tdnn/exp/pretrained.pt \
-            --HLG ./data/lang_phone/HLG.pt \
-            --words-file ./data/lang_phone/words.txt \
-            download/waves_yesno/0_0_0_1_0_0_0_1.wav \
-            download/waves_yesno/0_0_1_0_0_0_1_0.wav
-
-      - name: Test exporting to torchscript
-        shell: bash
-        working-directory: ${{github.workspace}}
-        run: |
-          export PYTHONPATH=$PWD:$PYTHONPATH
-          echo $PYTHONPATH
-
-          cd egs/yesno/ASR
-          python3 ./tdnn/export.py --epoch 14 --avg 2 --jit 1
-
-          python3 ./tdnn/jit_pretrained.py \
-            --nn-model ./tdnn/exp/cpu_jit.pt \
-            --HLG ./data/lang_phone/HLG.pt \
-            --words-file ./data/lang_phone/words.txt \
-            download/waves_yesno/0_0_0_1_0_0_0_1.wav \
-            download/waves_yesno/0_0_1_0_0_0_1_0.wav
-
-      - name: Test exporting to onnx
-        shell: bash
-        working-directory: ${{github.workspace}}
-        run: |
-          export PYTHONPATH=$PWD:$PYTHONPATH
-          echo $PYTHONPATH
-
-          cd egs/yesno/ASR
-          python3 ./tdnn/export_onnx.py --epoch 14 --avg 2
-
-          echo "Test float32 model"
-          python3 ./tdnn/onnx_pretrained.py \
-            --nn-model ./tdnn/exp/model-epoch-14-avg-2.onnx \
-            --HLG ./data/lang_phone/HLG.pt \
-            --words-file ./data/lang_phone/words.txt \
-            download/waves_yesno/0_0_0_1_0_0_0_1.wav \
-            download/waves_yesno/0_0_1_0_0_0_1_0.wav
-
-
-          echo "Test int8 model"
-          python3 ./tdnn/onnx_pretrained.py \
-            --nn-model ./tdnn/exp/model-epoch-14-avg-2.int8.onnx \
-            --HLG ./data/lang_phone/HLG.pt \
-            --words-file ./data/lang_phone/words.txt \
-            download/waves_yesno/0_0_0_1_0_0_0_1.wav \
-            download/waves_yesno/0_0_1_0_0_0_1_0.wav
-
-      - name: Test decoding with H
-        shell: bash
-        working-directory: ${{github.workspace}}
-        run: |
-          export PYTHONPATH=$PWD:$PYTHONPATH
-          echo $PYTHONPATH
-
-          cd egs/yesno/ASR
-          python3 ./tdnn/export.py --epoch 14 --avg 2 --jit 1
-
-          python3 ./tdnn/jit_pretrained_decode_with_H.py \
-              --nn-model ./tdnn/exp/cpu_jit.pt \
-              --H ./data/lang_phone/H.fst \
-              --tokens ./data/lang_phone/tokens.txt \
-              ./download/waves_yesno/0_0_0_1_0_0_0_1.wav \
-              ./download/waves_yesno/0_0_1_0_0_0_1_0.wav \
-              ./download/waves_yesno/0_0_1_0_0_1_1_1.wav
-
-      - name: Test decoding with HL
-        shell: bash
-        working-directory: ${{github.workspace}}
-        run: |
-          export PYTHONPATH=$PWD:$PYTHONPATH
-          echo $PYTHONPATH
-
-          cd egs/yesno/ASR
-          python3 ./tdnn/export.py --epoch 14 --avg 2 --jit 1
-
-          python3 ./tdnn/jit_pretrained_decode_with_HL.py \
-              --nn-model ./tdnn/exp/cpu_jit.pt \
-              --HL ./data/lang_phone/HL.fst \
-              --words ./data/lang_phone/words.txt \
-              ./download/waves_yesno/0_0_0_1_0_0_0_1.wav \
-              ./download/waves_yesno/0_0_1_0_0_0_1_0.wav \
-              ./download/waves_yesno/0_0_1_0_0_1_1_1.wav
-
-      - name: Show generated files
-        shell: bash
-        working-directory: ${{github.workspace}}
-        run: |
-          cd egs/yesno/ASR
-          ls -lh tdnn/exp
-          ls -lh data/lang_phone
+              .github/scripts/yesno/ASR/run.sh
diff --git a/.github/workflows/train-librispeech.yml b/.github/workflows/train-librispeech.yml
index 619b5ccc3..79002a881 100644
--- a/.github/workflows/train-librispeech.yml
+++ b/.github/workflows/train-librispeech.yml
@@ -64,6 +64,8 @@ jobs:
               --volume ${{ github.workspace }}/:/icefall
             shell: bash
             run: |
-              ls -lh /icefall
+              export PYTHONPATH=/icefall:$PYTHONPATH
+              cd /icefall
+              git config --global --add safe.directory /icefall
 
-              /icefall/.github/scripts/docker/run.sh
+              .github/scripts/librispeech/ASR/run.sh