Merge with master

.github/scripts/node-addon/package-optional.json

@@ -1,7 +1,7 @@
 {
   "name": "sherpa-onnx-PLATFORM2-ARCH",
   "version": "SHERPA_ONNX_VERSION",
-  "description": "Speech-to-text and text-to-speech using Next-gen Kaldi without internet connection",
+  "description": "Speech-to-text, text-to-speech, and speaker diarization using Next-gen Kaldi without internet connection",
   "main": "index.js",
   "scripts": {
     "test": "echo \"Error: no test specified\" && exit 1"
@@ -16,8 +16,18 @@
     "transcription",
     "real-time speech recognition",
     "without internet connection",
+    "locally",
+    "local",
     "embedded systems",
     "open source",
+    "diarization",
+    "speaker diarization",
+    "speaker recognition",
+    "speaker",
+    "speaker segmentation",
+    "speaker verification",
+    "spoken language identification",
+    "sherpa",
     "zipformer",
     "asr",
     "tts",
@@ -30,13 +40,13 @@
     "offline",
     "privacy",
     "open source",
-    "vad",
-    "speaker id",
-    "language id",
-    "node-addon-api",
     "streaming speech recognition",
     "speech",
-    "recognition"
+    "recognition",
+    "vad",
+    "node-addon-api",
+    "speaker id",
+    "language id"
   ],
   "author": "The next-gen Kaldi team",
   "license": "Apache-2.0",

.github/scripts/node-addon/package.json

@@ -1,7 +1,7 @@
 {
   "name": "sherpa-onnx-node",
   "version": "SHERPA_ONNX_VERSION",
-  "description": "Speech-to-text and text-to-speech using Next-gen Kaldi without internet connection",
+  "description": "Speech-to-text, text-to-speech, and speaker diarization using Next-gen Kaldi without internet connection",
   "main": "sherpa-onnx.js",
   "scripts": {
     "test": "echo \"Error: no test specified\" && exit 1"
@@ -16,8 +16,18 @@
     "transcription",
     "real-time speech recognition",
     "without internet connection",
+    "locally",
+    "local",
     "embedded systems",
     "open source",
+    "diarization",
+    "speaker diarization",
+    "speaker recognition",
+    "speaker",
+    "speaker segmentation",
+    "speaker verification",
+    "spoken language identification",
+    "sherpa",
     "zipformer",
     "asr",
     "tts",
@@ -30,13 +40,13 @@
     "offline",
     "privacy",
     "open source",
-    "vad",
-    "speaker id",
-    "language id",
-    "node-addon-api",
     "streaming speech recognition",
     "speech",
-    "recognition"
+    "recognition",
+    "vad",
+    "node-addon-api",
+    "speaker id",
+    "language id"
   ],
   "author": "The next-gen Kaldi team",
   "license": "Apache-2.0",
@@ -49,6 +59,7 @@
     "sherpa-onnx-darwin-x64": "^SHERPA_ONNX_VERSION",
     "sherpa-onnx-linux-x64": "^SHERPA_ONNX_VERSION",
     "sherpa-onnx-linux-arm64": "^SHERPA_ONNX_VERSION",
-    "sherpa-onnx-win-x64": "^SHERPA_ONNX_VERSION"
+    "sherpa-onnx-win-x64": "^SHERPA_ONNX_VERSION",
+    "sherpa-onnx-win-ia32": "^SHERPA_ONNX_VERSION"
   }
 }

.github/scripts/node-addon/run.sh

@@ -9,16 +9,23 @@ platform=$(node -p "require('os').platform()")
 
 arch=$(node -p "require('os').arch()")
 
+echo "platform: $platform"
+echo "arch: $arch"
+
+# ia32 for win x86
+
 platform2=$platform
 
+
 if [[ $platform == win32 ]]; then
   platform2=win
 fi
 
+
 SHERPA_ONNX_VERSION=$(grep "SHERPA_ONNX_VERSION" ./CMakeLists.txt  | cut -d " " -f 2  | cut -d '"' -f 2)
 echo "SHERPA_ONNX_VERSION $SHERPA_ONNX_VERSION"
 
-# SHERPA_ONNX_VERSION=1.0.28
+# SHERPA_ONNX_VERSION=1.0.31
 
 if [ -z $owner ]; then
   owner=k2-fsa

.github/scripts/test-dart.sh

@@ -4,17 +4,65 @@ set -ex
 
 cd dart-api-examples
 
-pushd non-streaming-asr
+pushd speaker-diarization
+echo '----------speaker diarization----------'
+./run.sh
+popd
 
-echo '----------paraformer itn----------'
-./run-paraformer-itn.sh
+pushd speaker-identification
+echo '----------3d speaker----------'
+./run-3d-speaker.sh
+popd
 
-echo '----------paraformer----------'
+pushd add-punctuations
+echo '----------CT Transformer----------'
+./run-ct-transformer.sh
+popd
+
+pushd audio-tagging
+echo '----------zipformer----------'
+./run-zipformer.sh
+
+echo '----------ced----------'
+./run-ced.sh
+popd
+
+pushd vad-with-non-streaming-asr
+echo '----------TeleSpeech CTC----------'
+./run-telespeech-ctc.sh
+rm -rf sherpa-onnx-*
+
+echo "----zipformer transducer----"
+./run-zipformer-transducer.sh
+rm -rf sherpa-onnx-*
+
+echo "----whisper----"
+./run-whisper.sh
+rm -rf sherpa-onnx-*
+
+echo "----paraformer----"
 ./run-paraformer.sh
 rm -rf sherpa-onnx-*
 
-echo '----------VAD with paraformer----------'
-./run-vad-with-paraformer.sh
+echo "----SenseVoice zh----"
+./run-sense-voice-zh-2.sh
+./run-sense-voice-zh.sh
+rm -rf sherpa-onnx-*
+
+echo "----SenseVoice en----"
+./run-sense-voice-en.sh
+rm -rf sherpa-onnx-*
+
+popd
+
+pushd keyword-spotter
+./run-zh.sh
+popd
+
+pushd non-streaming-asr
+
+echo '----------SenseVoice----------'
+./run-sense-voice.sh
 rm -rf sherpa-onnx-*
 
 echo '----------NeMo transducer----------'
@@ -37,6 +85,17 @@ echo '----------zipformer transducer----------'
 ./run-zipformer-transducer.sh
 rm -rf sherpa-onnx-*
 
+echo '----------paraformer itn----------'
+./run-paraformer-itn.sh
+
+echo '----------paraformer----------'
+./run-paraformer.sh
+rm -rf sherpa-onnx-*
+
+echo '----------VAD with paraformer----------'
+./run-vad-with-paraformer.sh
+rm -rf sherpa-onnx-*
+
 popd # non-streaming-asr
 
 pushd tts

.github/scripts/test-dot-net.sh

@@ -2,36 +2,76 @@
 
 cd dotnet-examples/
 
-cd ./online-decode-files
-./run-transducer-itn.sh
-./run-zipformer2-ctc.sh
-./run-transducer.sh
-./run-paraformer.sh
+cd ./offline-speaker-diarization
+./run.sh
+rm -rfv *.onnx
+rm -fv *.wav
+rm -rfv sherpa-onnx-pyannote-*
 
 cd ../offline-decode-files
+./run-sense-voice-ctc.sh
+rm -rf sherpa-onnx-*
+
 ./run-paraformer-itn.sh
+rm -rf sherpa-onnx-*
+
 ./run-telespeech-ctc.sh
+rm -rf sherpa-onnx-*
+
 ./run-nemo-ctc.sh
+rm -rf sherpa-onnx-*
+
 ./run-paraformer.sh
+rm -rf sherpa-onnx-*
+
 ./run-zipformer.sh
+rm -rf sherpa-onnx-*
+
 ./run-hotwords.sh
+rm -rf sherpa-onnx-*
+
 ./run-whisper.sh
+rm -rf sherpa-onnx-*
+
+./run-whisper-large-v3.sh
+rm -rf sherpa-onnx-*
+
 ./run-tdnn-yesno.sh
+rm -rf sherpa-onnx-*
+
+cd ../keyword-spotting-from-files
+./run.sh
+
+cd ../online-decode-files
+./run-transducer-itn.sh
+rm -rf sherpa-onnx-*
+
+./run-zipformer2-ctc.sh
+rm -rf sherpa-onnx-*
+
+./run-transducer.sh
+rm -rf sherpa-onnx-*
+
+./run-paraformer.sh
+rm -rf sherpa-onnx-*
 
 cd ../vad-non-streaming-asr-paraformer
 ./run.sh
 
 cd ../offline-punctuation
 ./run.sh
+rm -rf sherpa-onnx-*
 
 cd ../speaker-identification
 ./run.sh
 
 cd ../streaming-hlg-decoding/
 ./run.sh
+rm -rf sherpa-onnx-*
 
 cd ../spoken-language-identification
 ./run.sh
+rm -rf sherpa-onnx-*
 
 cd ../offline-tts
 ./run-aishell3.sh