Support adding punctuations to the speech recogntion result (#761)

.github/scripts/test-offline-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 model                             "
+log "------------------------------------------------------------"
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/punctuation-models/sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12.tar.bz2
+tar xvf sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12.tar.bz2
+rm sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12.tar.bz2
+repo=sherpa-onnx-punct-ct-transformer-zh-en-vocab272727-2024-04-12
+ls -lh $repo
+
+$EXE \
+ --debug=1 \
+ --ct-transformer=$repo/model.onnx \
+ "这是一个测试你好吗How are you我很好thank you are you ok谢谢你"
+
+$EXE \
+ --debug=1 \
+ --ct-transformer=$repo/model.onnx \
+ "我们都是木头人不会说话不会动"
+
+$EXE \
+ --debug=1 \
+ --ct-transformer=$repo/model.onnx \
+ "The African blogosphere is rapidly expanding bringing more voices online in the form of commentaries opinions analyses rants and poetry"
+
+rm -rf $repo

.github/workflows/linux.yaml

@@ -16,6 +16,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -34,6 +35,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -126,6 +128,14 @@ jobs:
           name: release-${{ matrix.build_type }}-with-shared-lib-${{ matrix.shared_lib }}-with-tts-${{ matrix.with_tts }}
           path: build/bin/*
 
+      - name: Test offline punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin:$PATH
+          export EXE=sherpa-onnx-offline-punctuation
+
+          .github/scripts/test-offline-punctuation.sh
+
       - name: Test C API
         shell: bash
         run: |

.github/workflows/macos.yaml

@@ -16,6 +16,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -33,6 +34,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -105,6 +107,14 @@ jobs:
           otool -L build/bin/sherpa-onnx
           otool -l build/bin/sherpa-onnx
 
+      - name: Test offline punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin:$PATH
+          export EXE=sherpa-onnx-offline-punctuation
+
+          .github/scripts/test-offline-punctuation.sh
+
       - name: Test C API
         shell: bash
         run: |

.github/workflows/windows-x64.yaml

@@ -15,6 +15,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -30,6 +31,7 @@ on:
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -72,6 +74,14 @@ jobs:
 
           ls -lh ./bin/Release/sherpa-onnx.exe
 
+      - name: Test offline punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin/Release:$PATH
+          export EXE=sherpa-onnx-offline-punctuation.exe
+
+          .github/scripts/test-offline-punctuation.sh
+
       - name: Test C API
         shell: bash
         run: |
@@ -82,7 +92,6 @@ jobs:
 
           .github/scripts/test-c-api.sh
 
-
       - name: Test Audio tagging
         shell: bash
         run: |

.github/workflows/windows-x86.yaml

@@ -15,6 +15,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -30,6 +31,7 @@ on:
       - '.github/scripts/test-offline-tts.sh'
       - '.github/scripts/test-online-ctc.sh'
       - '.github/scripts/test-audio-tagging.sh'
+      - '.github/scripts/test-offline-punctuation.sh'
       - 'CMakeLists.txt'
       - 'cmake/**'
       - 'sherpa-onnx/csrc/*'
@@ -72,6 +74,14 @@ jobs:
 
           ls -lh ./bin/Release/sherpa-onnx.exe
 
+      - name: Test offline punctuation
+        shell: bash
+        run: |
+          export PATH=$PWD/build/bin/Release:$PATH
+          export EXE=sherpa-onnx-offline-punctuation.exe
+
+          .github/scripts/test-offline-punctuation.sh
+
       - name: Test spoken language identification (C API)
         shell: bash
         run: |