Add CI tests for online punctuation models (#1226)

.github/scripts/test-online-punctuation.sh

@@ -0,0 +1,41 @@
+#!/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]}) $*"
+}
+
+echo "EXE is $EXE"
+echo "PATH: $PATH"
+
+which $EXE
+
+log "------------------------------------------------------------"
+log "Download the punctuation model                             "
+log "------------------------------------------------------------"
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/punctuation-models/sherpa-onnx-online-punct-en-2024-08-06.tar.bz2
+
+tar xvf sherpa-onnx-online-punct-en-2024-08-06.tar.bz2
+rm sherpa-onnx-online-punct-en-2024-08-06.tar.bz2
+repo=sherpa-onnx-online-punct-en-2024-08-06
+ls -lh $repo
+
+for m in model.onnx model.int8.onnx; do
+  $EXE \
+   --debug=1 \
+   --cnn-bilstm=$repo/$m \
+   --bpe-vocab=$repo/bpe.vocab \
+   "How are you i am fine thank you"
+
+  $EXE \
+   --debug=1 \
+   --cnn-bilstm=$repo/$m \
+   --bpe-vocab=$repo/bpe.vocab \
+   "The African blogosphere is rapidly expanding bringing more voices online in the form of commentaries opinions analyses rants and poetry"
+done
+
+rm -rf $repo

.github/workflows/linux.yaml

@@ -17,6 +17,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -36,6 +37,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -141,6 +143,16 @@ jobs:
           name: release-${{ matrix.build_type }}-with-shared-lib-${{ matrix.shared_lib }}-with-tts-${{ matrix.with_tts }}
           path: install/*
 
+      - name: Test online punctuation
+        shell: bash
+        run: |
+          du -h -d1 .
+          export PATH=$PWD/build/bin:$PATH
+          export EXE=sherpa-onnx-online-punctuation
+
+          .github/scripts/test-online-punctuation.sh
+          du -h -d1 .
+
       - name: Test offline transducer
         shell: bash
         run: |

.github/workflows/macos.yaml

@@ -17,6 +17,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -35,6 +36,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -113,6 +115,14 @@ jobs:
           otool -L build/bin/sherpa-onnx
           otool -l build/bin/sherpa-onnx
 
+      - name: Test online punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin:$PATH
+          export EXE=sherpa-onnx-online-punctuation
+
+          .github/scripts/test-online-punctuation.sh
+
       - name: Test offline transducer
         shell: bash
         run: |

.github/workflows/sanitizer.yaml

@@ -76,6 +76,14 @@ jobs:
           otool -L build/bin/sherpa-onnx
           otool -l build/bin/sherpa-onnx
 
+      - name: Test online punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin:$PATH
+          export EXE=sherpa-onnx-online-punctuation
+
+          .github/scripts/test-online-punctuation.sh
+
       - name: Test offline punctuation
         shell: bash
         run: |

.github/workflows/windows-x64.yaml

@@ -16,6 +16,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -32,6 +33,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -85,6 +87,14 @@ jobs:
           name: release-windows-x64-${{ matrix.shared_lib }}-${{ matrix.with_tts }}
           path: build/install/*
 
+      - name: Test online punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin/Release:$PATH
+          export EXE=sherpa-onnx-online-punctuation.exe
+
+          .github/scripts/test-online-punctuation.sh
+
       - name: Test offline punctuation
         shell: bash
         run: |

.github/workflows/windows-x86.yaml

@@ -16,6 +16,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -32,6 +33,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
       - '.github/scripts/test-offline-punctuation.sh'
+      - '.github/scripts/test-online-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -85,6 +87,14 @@ jobs:
           name: release-windows-x86-${{ matrix.shared_lib }}-${{ matrix.with_tts }}
           path: build/install/*
 
+      - name: Test online punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin/Release:$PATH
+          export EXE=sherpa-onnx-online-punctuation.exe
+
+          .github/scripts/test-online-punctuation.sh
+
       - name: Test offline punctuation
         shell: bash
         run: |