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:
50
java-api-examples/NonStreamingDecodeFileZipformerCtc.java
Normal file
50
java-api-examples/NonStreamingDecodeFileZipformerCtc.java
Normal file
@@ -0,0 +1,50 @@
|
||||
// Copyright 2025 Xiaomi Corporation
|
||||
|
||||
// This file shows how to use an offline Zipformer CTC model,
|
||||
// i.e., non-streaming Zipformer CTC model,
|
||||
// to decode files.
|
||||
import com.k2fsa.sherpa.onnx.*;
|
||||
|
||||
public class NonStreamingDecodeFileZipformerCtc {
|
||||
public static void main(String[] args) {
|
||||
// please refer to
|
||||
// https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03.tar.bz2
|
||||
// to download model files
|
||||
String model = "./sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03/model.int8.onnx";
|
||||
String tokens = "./sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03/tokens.txt";
|
||||
|
||||
String waveFilename = "./sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03/test_wavs/0.wav";
|
||||
|
||||
WaveReader reader = new WaveReader(waveFilename);
|
||||
|
||||
OfflineZipformerCtcModelConfig zipformerCtc =
|
||||
OfflineZipformerCtcModelConfig.builder().setModel(model).build();
|
||||
|
||||
OfflineModelConfig modelConfig =
|
||||
OfflineModelConfig.builder()
|
||||
.setZipformerCtc(zipformerCtc)
|
||||
.setTokens(tokens)
|
||||
.setNumThreads(1)
|
||||
.setDebug(true)
|
||||
.build();
|
||||
|
||||
OfflineRecognizerConfig config =
|
||||
OfflineRecognizerConfig.builder()
|
||||
.setOfflineModelConfig(modelConfig)
|
||||
.setDecodingMethod("greedy_search")
|
||||
.build();
|
||||
|
||||
OfflineRecognizer recognizer = new OfflineRecognizer(config);
|
||||
OfflineStream stream = recognizer.createStream();
|
||||
stream.acceptWaveform(reader.getSamples(), reader.getSampleRate());
|
||||
|
||||
recognizer.decode(stream);
|
||||
|
||||
String text = recognizer.getResult(stream).getText();
|
||||
|
||||
System.out.printf("filename:%s\nresult:%s\n", waveFilename, text);
|
||||
|
||||
stream.release();
|
||||
recognizer.release();
|
||||
}
|
||||
}
|
||||
38
java-api-examples/run-non-streaming-decode-file-zipformer-ctc.sh
Executable file
38
java-api-examples/run-non-streaming-decode-file-zipformer-ctc.sh
Executable file
@@ -0,0 +1,38 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -ex
|
||||
|
||||
if [[ ! -f ../build/lib/libsherpa-onnx-jni.dylib && ! -f ../build/lib/libsherpa-onnx-jni.so ]]; then
|
||||
mkdir -p ../build
|
||||
pushd ../build
|
||||
cmake \
|
||||
-DSHERPA_ONNX_ENABLE_PYTHON=OFF \
|
||||
-DSHERPA_ONNX_ENABLE_TESTS=OFF \
|
||||
-DSHERPA_ONNX_ENABLE_CHECK=OFF \
|
||||
-DBUILD_SHARED_LIBS=ON \
|
||||
-DSHERPA_ONNX_ENABLE_PORTAUDIO=OFF \
|
||||
-DSHERPA_ONNX_ENABLE_JNI=ON \
|
||||
..
|
||||
|
||||
make -j4
|
||||
ls -lh lib
|
||||
popd
|
||||
fi
|
||||
|
||||
if [ ! -f ../sherpa-onnx/java-api/build/sherpa-onnx.jar ]; then
|
||||
pushd ../sherpa-onnx/java-api
|
||||
make
|
||||
popd
|
||||
fi
|
||||
|
||||
if [ ! -f ./sherpa-onnx-zipformer-ctc-zh-int8-2025-07-03/tokens.txt ]; then
|
||||
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
|
||||
fi
|
||||
|
||||
java \
|
||||
-Djava.library.path=$PWD/../build/lib \
|
||||
-cp ../sherpa-onnx/java-api/build/sherpa-onnx.jar \
|
||||
NonStreamingDecodeFileZipformerCtc.java
|
||||
Reference in New Issue
Block a user