C# API for streaming zipformer2 CTC

.github/workflows/test-dot-net.yaml

@@ -61,7 +61,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, macos-latest]
+        os: [ubuntu-latest, macos-latest] #, windows-latest]
         python-version: ["3.8"]
 
     steps:
@@ -143,6 +143,7 @@ jobs:
           cd dotnet-examples/
 
           cd online-decode-files
+          ./run-zipformer2-ctc.sh
           ./run-transducer.sh
           ./run-paraformer.sh
 

dotnet-examples/.gitignore

@@ -1,2 +1,3 @@
 bin
 obj
+!*.sh

dotnet-examples/online-decode-files/Program.cs

@@ -38,6 +38,9 @@ class Options
     [Option("paraformer-decoder", Required = false, HelpText = "Path to paraformer decoder.onnx")]
     public string ParaformerDecoder { get; set; }
 
+    [Option("zipformer2-ctc", Required = false, HelpText = "Path to zipformer2 CTC onnx model")]
+    public string Zipformer2Ctc { get; set; }
+
     [Option("num-threads", Required = false, Default = 1, HelpText = "Number of threads for computation")]
     public int NumThreads { get; set; }
 
@@ -107,7 +110,19 @@ dotnet run \
   --files ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/test_wavs/0.wav \
   ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/test_wavs/1.wav
 
-(2) Streaming Paraformer models
+(2) Streaming Zipformer2 Ctc models
+
+dotnet run -c Release \
+  --tokens ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/tokens.txt \
+  --zipformer2-ctc ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/ctc-epoch-20-avg-1-chunk-16-left-128.onnx \
+  --files ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000000.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000001.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000002.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/TEST_MEETING_T0000000113.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/TEST_MEETING_T0000000219.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/TEST_MEETING_T0000000351.wav
+
+(3) Streaming Paraformer models
 dotnet run \
   --tokens=./sherpa-onnx-streaming-paraformer-bilingual-zh-en/tokens.txt \
   --paraformer-encoder=./sherpa-onnx-streaming-paraformer-bilingual-zh-en/encoder.int8.onnx \
@@ -121,6 +136,7 @@ dotnet run \
 Please refer to
 https://k2-fsa.github.io/sherpa/onnx/pretrained_models/online-transducer/index.html
 https://k2-fsa.github.io/sherpa/onnx/pretrained_models/online-paraformer/index.html
+https://k2-fsa.github.io/sherpa/onnx/pretrained_models/online-ctc/index.html
 to download pre-trained streaming models.
 ";
 
@@ -150,6 +166,8 @@ private static void Run(Options options)
     config.ModelConfig.Paraformer.Encoder = options.ParaformerEncoder;
     config.ModelConfig.Paraformer.Decoder = options.ParaformerDecoder;
 
+    config.ModelConfig.Zipformer2Ctc.Model = options.Zipformer2Ctc;
+
     config.ModelConfig.Tokens = options.Tokens;
     config.ModelConfig.Provider = options.Provider;
     config.ModelConfig.NumThreads = options.NumThreads;

dotnet-examples/online-decode-files/run-zipformer2-ctc.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+
+# Please refer to
+# https://k2-fsa.github.io/sherpa/onnx/pretrained_models/online-ctc/zipformer-ctc-models.html#sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13-chinese
+# to download the model files
+
+if [ ! -d ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13 ]; then
+  curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
+  tar xvf sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
+  rm sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13.tar.bz2
+fi
+
+dotnet run -c Release \
+  --tokens ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/tokens.txt \
+  --zipformer2-ctc ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/ctc-epoch-20-avg-1-chunk-16-left-128.onnx \
+  --files ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000000.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000001.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/DEV_T0000000002.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/TEST_MEETING_T0000000113.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/TEST_MEETING_T0000000219.wav \
+  ./sherpa-onnx-streaming-zipformer-ctc-multi-zh-hans-2023-12-13/test_wavs/TEST_MEETING_T0000000351.wav

scripts/dotnet/online.cs

@@ -50,13 +50,26 @@ public OnlineParaformerModelConfig()
     public string Decoder;
   }
 
+  [StructLayout(LayoutKind.Sequential)]
+  public struct OnlineZipformer2CtcModelConfig
+  {
+    public OnlineZipformer2CtcModelConfig()
+    {
+      Model = "";
+    }
+
+    [MarshalAs(UnmanagedType.LPStr)]
+    public string Model;
+  }
+
   [StructLayout(LayoutKind.Sequential)]
   public struct OnlineModelConfig
   {
     public OnlineModelConfig()
     {
       Transducer = new OnlineTransducerModelConfig();
       Paraformer = new OnlineParaformerModelConfig();
+      Zipformer2Ctc = new OnlineZipformer2CtcModelConfig();
       Tokens = "";
       NumThreads = 1;
       Provider = "cpu";
@@ -66,6 +79,7 @@ public OnlineModelConfig()
 
     public OnlineTransducerModelConfig Transducer;
     public OnlineParaformerModelConfig Paraformer;
+    public OnlineZipformer2CtcModelConfig Zipformer2Ctc;
 
     [MarshalAs(UnmanagedType.LPStr)]
     public string Tokens;