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:
75
.github/scripts/test-dot-net.sh
vendored
75
.github/scripts/test-dot-net.sh
vendored
@@ -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-*
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user