[WIP] Fetch upstream

.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",

.github/scripts/test-cxx-api.sh

@@ -0,0 +1,42 @@
+#!/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 "CXX_STREAMING_ZIPFORMER_EXE is $CXX_STREAMING_ZIPFORMER_EXE"
+echo "CXX_WHISPER_EXE is $CXX_WHISPER_EXE"
+echo "CXX_SENSE_VOICE_EXE is $CXX_SENSE_VOICE_EXE"
+echo "PATH: $PATH"
+
+log "------------------------------------------------------------"
+log "Test streaming zipformer CXX API"
+log "------------------------------------------------------------"
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
+tar xvf sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
+rm sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20.tar.bz2
+$CXX_STREAMING_ZIPFORMER_EXE
+rm -rf sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20
+
+log "------------------------------------------------------------"
+log "Test Whisper CXX API"
+log "------------------------------------------------------------"
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-whisper-tiny.en.tar.bz2
+tar xvf sherpa-onnx-whisper-tiny.en.tar.bz2
+rm sherpa-onnx-whisper-tiny.en.tar.bz2
+$CXX_WHISPER_EXE
+rm -rf sherpa-onnx-whisper-tiny.en
+
+log "------------------------------------------------------------"
+log "Test SenseVoice CXX API"
+log "------------------------------------------------------------"
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
+tar xvf sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
+rm sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
+
+$CXX_SENSE_VOICE_EXE
+rm -rf sherpa-onnx-sense-voice-*

.github/scripts/test-dart.sh

@@ -4,6 +4,37 @@ set -ex
 
 cd dart-api-examples
 
+pushd tts
+
+echo '----------matcha tts----------'
+./run-kokoro-en.sh
+./run-matcha-zh.sh
+./run-matcha-en.sh
+ls -lh *.wav
+rm -rf matcha-icefall-*
+rm *.onnx
+
+echo '----------piper tts----------'
+./run-piper.sh
+rm -rf vits-piper-*
+
+echo '----------coqui tts----------'
+./run-coqui.sh
+rm -rf vits-coqui-*
+
+echo '----------zh tts----------'
+./run-vits-zh.sh
+rm -rf sherpa-onnx-*
+
+ls -lh *.wav
+
+popd # tts
+
+pushd speaker-diarization
+echo '----------speaker diarization----------'
+./run.sh
+popd
+
 pushd speaker-identification
 echo '----------3d speaker----------'
 ./run-3d-speaker.sh
@@ -31,6 +62,10 @@ echo "----zipformer transducer----"
 ./run-zipformer-transducer.sh
 rm -rf sherpa-onnx-*
 
+echo "----moonshine----"
+./run-moonshine.sh
+rm -rf sherpa-onnx-*
+
 echo "----whisper----"
 ./run-whisper.sh
 rm -rf sherpa-onnx-*
@@ -72,6 +107,10 @@ echo '----------TeleSpeech CTC----------'
 ./run-telespeech-ctc.sh
 rm -rf sherpa-onnx-*
 
+echo '----------moonshine----------'
+./run-moonshine.sh
+rm -rf sherpa-onnx-*
+
 echo '----------whisper----------'
 ./run-whisper.sh
 rm -rf sherpa-onnx-*
@@ -93,22 +132,6 @@ 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----------'

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

@@ -2,7 +2,41 @@
 
 cd dotnet-examples/
 
-cd ./offline-decode-files
+cd ./kokoro-tts
+./run-kokoro-en.sh
+ls -lh
+
+cd ../offline-tts
+./run-matcha-zh.sh
+ls -lh *.wav
+./run-matcha-en.sh
+ls -lh *.wav
+./run-aishell3.sh
+ls -lh *.wav
+./run-piper.sh
+ls -lh *.wav
+./run-hf-fanchen.sh
+ls -lh *.wav
+ls -lh
+
+pushd ../..
+
+mkdir tts
+
+cp -v dotnet-examples/kokoro-tts/*.wav ./tts
+cp -v dotnet-examples/offline-tts/*.wav ./tts
+popd
+
+cd ../offline-speaker-diarization
+./run.sh
+rm -rfv *.onnx
+rm -fv *.wav
+rm -rfv sherpa-onnx-pyannote-*
+
+cd ../offline-decode-files
+./run-moonshine.sh
+rm -rf sherpa-onnx-*
+
 ./run-sense-voice-ctc.sh
 rm -rf sherpa-onnx-*
 
@@ -67,14 +101,4 @@ cd ../spoken-language-identification
 ./run.sh
 rm -rf sherpa-onnx-*
 
-cd ../offline-tts
-./run-aishell3.sh
-./run-piper.sh
-./run-hf-fanchen.sh
-ls -lh
-
-cd ../..
-
-mkdir tts
 
-cp dotnet-examples/offline-tts/*.wav ./tts

.github/scripts/test-nodejs-addon-npm.sh

@@ -10,7 +10,34 @@ arch=$(node -p "require('os').arch()")
 platform=$(node -p "require('os').platform()")
 node_version=$(node -p "process.versions.node.split('.')[0]")
 
-echo "----------non-streaming asr + vad----------"
+echo "----------non-streaming asr moonshine + vad----------"
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
+tar xvf sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
+rm sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/Obama.wav
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx
+
+node ./test_vad_with_non_streaming_asr_moonshine.js
+rm -rf sherpa-onnx-*
+rm *.wav
+rm *.onnx
+
+echo "----------non-streaming speaker diarization----------"
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-segmentation-models/sherpa-onnx-pyannote-segmentation-3-0.tar.bz2
+tar xvf sherpa-onnx-pyannote-segmentation-3-0.tar.bz2
+rm sherpa-onnx-pyannote-segmentation-3-0.tar.bz2
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-recongition-models/3dspeaker_speech_eres2net_base_sv_zh-cn_3dspeaker_16k.onnx
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/speaker-segmentation-models/0-four-speakers-zh.wav
+
+node ./test_offline_speaker_diarization.js
+
+rm -rfv *.onnx *.wav sherpa-onnx-pyannote-*
+
+echo "----------non-streaming asr whisper + vad----------"
 curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-whisper-tiny.en.tar.bz2
 tar xvf sherpa-onnx-whisper-tiny.en.tar.bz2
 rm sherpa-onnx-whisper-tiny.en.tar.bz2
@@ -58,6 +85,32 @@ fi
 
 echo "----------tts----------"
 
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kokoro-en-v0_19.tar.bz2
+tar xf kokoro-en-v0_19.tar.bz2
+rm kokoro-en-v0_19.tar.bz2
+
+node ./test_tts_non_streaming_kokoro_en.js
+ls -lh *.wav
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-en_US-ljspeech.tar.bz2
+tar xvf matcha-icefall-en_US-ljspeech.tar.bz2
+rm matcha-icefall-en_US-ljspeech.tar.bz2
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/vocoder-models/hifigan_v2.onnx
+
+node ./test_tts_non_streaming_matcha_icefall_en.js
+rm hifigan_v2.onnx
+rm -rf matcha-icefall-en_US-ljspeech
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-zh-baker.tar.bz2
+tar xvf matcha-icefall-zh-baker.tar.bz2
+rm matcha-icefall-zh-baker.tar.bz2
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/vocoder-models/hifigan_v2.onnx
+
+node ./test_tts_non_streaming_matcha_icefall_zh.js
+rm hifigan_v2.onnx
+rm -rf matcha-icefall-zh-baker
+ls -lh *.wav
+
 curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_GB-cori-medium.tar.bz2
 tar xf vits-piper-en_GB-cori-medium.tar.bz2
 rm vits-piper-en_GB-cori-medium.tar.bz2
@@ -204,6 +257,11 @@ rm sherpa-onnx-whisper-tiny.en.tar.bz2
 node ./test_asr_non_streaming_whisper.js
 rm -rf sherpa-onnx-whisper-tiny.en
 
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
+tar xvf sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
+rm sherpa-onnx-moonshine-tiny-en-int8.tar.bz2
 
+node ./test_asr_non_streaming_moonshine.js
+rm -rf sherpa-onnx-*
 
 ls -lh