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
This commit is contained in:
Fangjun Kuang
2025-07-04 15:57:07 +08:00
committed by GitHub
parent ef16455cb5
commit 3bf986d08d
71 changed files with 2121 additions and 68 deletions

View File

@@ -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-*