Support non-streaming zipformer CTC ASR models (#2340)

This PR adds support for non-streaming Zipformer CTC ASR models across 
multiple language bindings, WebAssembly, examples, and CI workflows.

- Introduces a new OfflineZipformerCtcModelConfig in C/C++, Python, Swift, Java, Kotlin, Go, Dart, Pascal, and C# APIs
- Updates initialization, freeing, and recognition logic to include Zipformer CTC in WASM and Node.js
- Adds example scripts and CI steps for downloading, building, and running Zipformer CTC models

Model doc is available at
https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-ctc/icefall/zipformer.html

.github/scripts/test-dart.sh

@@ -6,6 +6,10 @@ cd dart-api-examples
 
 pushd non-streaming-asr
 
+echo '----------Zipformer CTC----------'
+./run-zipformer-ctc.sh
+rm -rf sherpa-onnx-*
+
 echo '----------SenseVoice----------'
 ./run-sense-voice-with-hr.sh
 ./run-sense-voice.sh
@@ -114,6 +118,10 @@ popd
 
 pushd vad-with-non-streaming-asr
 
+echo '----------Zipformer CTC----------'
+./run-zipformer-ctc.sh
+rm -rf sherpa-onnx-*
+
 echo '----------Dolphin CTC----------'
 ./run-dolphin-ctc.sh
 rm -rf sherpa-onnx-*

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

@@ -6,43 +6,11 @@ cd ./version-test
 ./run.sh
 ls -lh
 
-cd ../speech-enhancement-gtcrn
-./run.sh
-ls -lh
-
-cd ../kokoro-tts
-./run-kokoro.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-zipformer-ctc.sh
+rm -rf sherpa-onnx-*
+
 ./run-dolphin-ctc.sh
 rm -rf sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02
 
@@ -82,6 +50,41 @@ rm -rf sherpa-onnx-*
 ./run-tdnn-yesno.sh
 rm -rf sherpa-onnx-*
 
+cd ../speech-enhancement-gtcrn
+./run.sh
+ls -lh
+
+cd ../kokoro-tts
+./run-kokoro.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 ../keyword-spotting-from-files
 ./run.sh
 
@@ -115,5 +118,3 @@ rm -rf sherpa-onnx-*
 cd ../spoken-language-identification
 ./run.sh
 rm -rf sherpa-onnx-*
-
-

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

@@ -10,6 +10,15 @@ 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 Zipformer CTC----------"
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03.tar.bz2
+
+tar xvf sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03.tar.bz2
+rm sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03.tar.bz2
+
+node ./test_asr_non_streaming_zipformer_ctc.js
+rm -rf sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03
+
 echo "----------non-streaming ASR NeMo parakeet tdt----------"
 curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8.tar.bz2
 tar xvf sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8.tar.bz2

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

@@ -9,6 +9,15 @@ git status
 ls -lh
 ls -lh node_modules
 
+# asr with offline zipformer ctc
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03.tar.bz2
+
+tar xvf sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03.tar.bz2
+rm sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03.tar.bz2
+
+node ./test-offline-zipformer-ctc.js
+rm -rf sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03
+
 # asr with offline dolphin ctc
 curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02.tar.bz2
 tar xvf sherpa-onnx-dolphin-base-ctc-multi-lang-int8-2025-04-02.tar.bz2

.github/scripts/test-swift.sh

@@ -9,6 +9,9 @@ ls -lh
 
 ./run-test-version.sh
 
+./run-zipformer-ctc-asr.sh
+rm -rf sherpa-onnx-zipformer-*
+
 ./run-decode-file-sense-voice-with-hr.sh
 rm -rf sherpa-onnx-sense-voice-*
 rm -rf dict lexicon.txt replace.fst test-hr.wav

.github/workflows/aarch64-linux-gnu-shared.yaml

@@ -89,6 +89,7 @@ jobs:
           make -j4 install
 
           cp -v bin/sense-voice-simulate-streaming-alsa-cxx-api install/bin
+          cp -v bin/zipformer-ctc-simulate-streaming-alsa-cxx-api install/bin
 
           rm -rf install/lib/pkgconfig
           rm -fv install/lib/cargs.h
@@ -135,6 +136,7 @@ jobs:
               make -j4 install
 
               cp -v bin/sense-voice-simulate-streaming-alsa-cxx-api install/bin
+              cp -v bin/zipformer-ctc-simulate-streaming-alsa-cxx-api install/bin
 
               rm -rf install/lib/pkgconfig
               rm -fv install/lib/cargs.h

.github/workflows/aarch64-linux-gnu-static.yaml

@@ -90,6 +90,7 @@ jobs:
               make install
 
               cp bin/sense-voice-simulate-streaming-alsa-cxx-api install/bin
+              cp bin/zipformer-ctc-simulate-streaming-alsa-cxx-api install/bin
 
               ls -lh install/lib
 

.github/workflows/pascal.yaml

@@ -37,7 +37,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, macos-latest, macos-13, windows-latest]
+        os: [ubuntu-latest, macos-latest, macos-13, windows-latest, ubuntu-22.04-arm]
 
     steps:
       - uses: actions/checkout@v4
@@ -56,7 +56,7 @@ jobs:
           key: ${{ matrix.os }}
 
       - name: Install Free pascal compiler (ubuntu)
-        if: matrix.os == 'ubuntu-latest'
+        if: matrix.os == 'ubuntu-latest' || matrix.os == 'ubuntu-22.04-arm'
         shell: bash
         run: |
           sudo apt-get update
@@ -156,6 +156,10 @@ jobs:
 
           pushd non-streaming-asr
 
+          ./run-zipformer-ctc.sh
+          rm -rf sherpa-onnx-*
+          echo "---"
+
           ./run-dolphin-ctc.sh
           rm -rf sherpa-onnx-*
           echo "---"
@@ -264,9 +268,12 @@ jobs:
 
           cd ./pascal-api-examples
 
-
           pushd vad-with-non-streaming-asr
 
+          time ./run-vad-with-zipformer-ctc.sh
+          rm -rf sherpa-onnx-*
+          echo "---"
+
           time ./run-vad-with-dolphin-ctc.sh
           rm -rf sherpa-onnx-*
           echo "---"

.github/workflows/run-java-test.yaml

@@ -165,6 +165,9 @@ jobs:
         run: |
           cd ./java-api-examples
 
+          ./run-non-streaming-decode-file-zipformer-ctc.sh
+          rm -rf sherpa-onnx-zipformer-ctc-*
+
           ./run-non-streaming-decode-file-dolphin-ctc.sh
           rm -rf sherpa-onnx-dolphin-*
 

.github/workflows/test-go.yaml

@@ -184,6 +184,10 @@ jobs:
           go build
           ls -lh
 
+          echo "Test Zipformer CTC"
+          ./run-zipformer-ctc.sh
+          rm -rf sherpa-onnx-zipformer-*
+
           echo "Test SenseVoice ctc"
           ./run-sense-voice-small-with-hr.sh
           ./run-sense-voice-small.sh

.github/workflows/upload-models.yaml

@@ -19,12 +19,36 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.8"]
+        python-version: ["3.10"]
 
     steps:
       - uses: actions/checkout@v4
 
+      - name: Zipformer CTC (non-streaming)
+        shell: bash
+        run: |
+          git lfs install
+          names=(
+            sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03
+            sherpa-onnx-zipformer-ctc-zh-2025-07-03
+            sherpa-onnx-zipformer-ctc-zh-fp16-2025-07-03
+          )
+          for name in ${names[@]}; do
+            git clone https://huggingface.co/csukuangfj/$name 
+            pushd $name
+            git lfs pull
+            rm -rf .git
+            rm -rfv .gitattributes
+            ls -lh
+            popd
+
+            tar cjfv $name.tar.bz2 $name
+            rm -rf $name
+            ls -lh *.tar.bz2
+          done
+
       - name: Vietnamese (zipformer)
+        if: false
         shell: bash
         run: |
           rm -rf models
@@ -76,6 +100,7 @@ jobs:
           mv models/* .
 
       - name: Publish to huggingface (Vietnamese zipformer)
+        if: false
         env:
           HF_TOKEN: ${{ secrets.HF_TOKEN }}
         uses: nick-fields/retry@v3