Merge with master

.clang-tidy

@@ -0,0 +1,73 @@
+---
+# NOTE there must be no spaces before the '-', so put the comma last.
+# The check bugprone-unchecked-optional-access is also turned off atm
+# because it causes clang-tidy to hang randomly. The tracking issue
+# can be found at https://github.com/llvm/llvm-project/issues/69369.
+#
+# Modified from
+# https://github.com/pytorch/pytorch/blob/main/.clang-tidy
+InheritParentConfig: true
+Checks: '
+bugprone-*,
+-bugprone-easily-swappable-parameters,
+-bugprone-forward-declaration-namespace,
+-bugprone-implicit-widening-of-multiplication-result,
+-bugprone-macro-parentheses,
+-bugprone-lambda-function-name,
+-bugprone-narrowing-conversions,
+-bugprone-reserved-identifier,
+-bugprone-swapped-arguments,
+-bugprone-unchecked-optional-access,
+clang-diagnostic-missing-prototypes,
+cppcoreguidelines-*,
+-cppcoreguidelines-avoid-const-or-ref-data-members,
+-cppcoreguidelines-avoid-do-while,
+-cppcoreguidelines-avoid-magic-numbers,
+-cppcoreguidelines-avoid-non-const-global-variables,
+-cppcoreguidelines-interfaces-global-init,
+-cppcoreguidelines-macro-usage,
+-cppcoreguidelines-narrowing-conversions,
+-cppcoreguidelines-owning-memory,
+-cppcoreguidelines-pro-bounds-array-to-pointer-decay,
+-cppcoreguidelines-pro-bounds-constant-array-index,
+-cppcoreguidelines-pro-bounds-pointer-arithmetic,
+-cppcoreguidelines-pro-type-const-cast,
+-cppcoreguidelines-pro-type-cstyle-cast,
+-cppcoreguidelines-pro-type-reinterpret-cast,
+-cppcoreguidelines-pro-type-static-cast-downcast,
+-cppcoreguidelines-pro-type-union-access,
+-cppcoreguidelines-pro-type-vararg,
+-cppcoreguidelines-special-member-functions,
+-cppcoreguidelines-non-private-member-variables-in-classes,
+-facebook-hte-RelativeInclude,
+hicpp-exception-baseclass,
+hicpp-avoid-goto,
+misc-*,
+-misc-const-correctness,
+-misc-include-cleaner,
+-misc-use-anonymous-namespace,
+-misc-unused-parameters,
+-misc-no-recursion,
+-misc-non-private-member-variables-in-classes,
+-misc-confusable-identifiers,
+modernize-*,
+-modernize-macro-to-enum,
+-modernize-pass-by-value,
+-modernize-return-braced-init-list,
+-modernize-use-auto,
+-modernize-use-default-member-init,
+-modernize-use-using,
+-modernize-use-trailing-return-type,
+-modernize-use-nodiscard,
+performance-*,
+readability-container-size-empty,
+readability-delete-null-pointer,
+readability-duplicate-include
+readability-misplaced-array-index,
+readability-redundant-function-ptr-dereference,
+readability-redundant-smartptr-get,
+readability-simplify-subscript-expr,
+readability-string-compare,
+'
+WarningsAsErrors: '*'
+...

.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

@@ -0,0 +1,147 @@
+#!/usr/bin/env bash
+
+set -ex
+
+cd dart-api-examples
+
+pushd speaker-diarization
+echo '----------speaker diarization----------'
+./run.sh
+popd
+
+pushd speaker-identification
+echo '----------3d speaker----------'
+./run-3d-speaker.sh
+popd
+
+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 "----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----------'
+./run-nemo-transducer.sh
+rm -rf sherpa-onnx-*
+
+echo '----------NeMo CTC----------'
+./run-nemo-ctc.sh
+rm -rf sherpa-onnx-*
+
+echo '----------TeleSpeech CTC----------'
+./run-telespeech-ctc.sh
+rm -rf sherpa-onnx-*
+
+echo '----------whisper----------'
+./run-whisper.sh
+rm -rf sherpa-onnx-*
+
+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
+
+echo '----------piper tts----------'
+./run-piper.sh
+rm -rf vits-piper-*
+
+echo '----------coqui tts----------'
+./run-coqui.sh
+rm -rf vits-coqui-*
+
+echo '----------zh tts----------'
+./run-zh.sh
+rm -rf sherpa-onnx-*
+
+popd # tts
+
+pushd streaming-asr
+
+echo '----------streaming zipformer ctc HLG----------'
+./run-zipformer-ctc-hlg.sh
+rm -rf sherpa-onnx-*
+
+echo '----------streaming zipformer ctc----------'
+./run-zipformer-ctc.sh
+rm -rf sherpa-onnx-*
+
+echo '----------streaming zipformer transducer----------'
+./run-zipformer-transducer-itn.sh
+./run-zipformer-transducer.sh
+rm -f itn*
+rm -rf sherpa-onnx-*
+
+echo '----------streaming NeMo transducer----------'
+./run-nemo-transducer.sh
+rm -rf sherpa-onnx-*
+
+echo '----------streaming paraformer----------'
+./run-paraformer.sh
+rm -rf sherpa-onnx-*
+
+popd # streaming-asr
+
+pushd vad
+./run.sh
+rm *.onnx
+popd
+