Add keyword spotting for C# (#1105)

This commit is contained in:
Fangjun Kuang
2024-07-10 21:18:46 +08:00
committed by GitHub
parent dd0ff2ca06
commit 08c758520f
21 changed files with 368 additions and 37 deletions

View File

@@ -0,0 +1,99 @@
// Copyright (c) 2024 Xiaomi Corporation
//
// This file shows how to do keyword spotting with sherpa-onnx.
//
// 1. Download a model from
// https://github.com/k2-fsa/sherpa-onnx/releases/tag/kws-models
//
// wget https://github.com/k2-fsa/sherpa-onnx/releases/download/kws-models/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
// tar xvf sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
//
// 2. Now run it
//
// dotnet run
using SherpaOnnx;
using System.Collections.Generic;
using System;
class KeywordSpotterDemo
{
static void Main(string[] args)
{
var config = new KeywordSpotterConfig();
config.FeatConfig.SampleRate = 16000;
config.FeatConfig.FeatureDim = 80;
config.ModelConfig.Transducer.Encoder = "./sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/encoder-epoch-12-avg-2-chunk-16-left-64.onnx";
config.ModelConfig.Transducer.Decoder = "./sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/decoder-epoch-12-avg-2-chunk-16-left-64.onnx";
config.ModelConfig.Transducer.Joiner = "./sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/joiner-epoch-12-avg-2-chunk-16-left-64.onnx";
config.ModelConfig.Tokens = "./sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/tokens.txt";
config.ModelConfig.Provider = "cpu";
config.ModelConfig.NumThreads = 1;
config.ModelConfig.Debug = 1;
config.KeywordsFile = "./sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/test_wavs/test_keywords.txt";
var kws = new KeywordSpotter(config);
var filename = "./sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/test_wavs/3.wav";
WaveReader waveReader = new WaveReader(filename);
Console.WriteLine("----------Use pre-defined keywords----------");
OnlineStream s = kws.CreateStream();
s.AcceptWaveform(waveReader.SampleRate, waveReader.Samples);
float[] tailPadding = new float[(int)(waveReader.SampleRate * 0.3)];
s.AcceptWaveform(waveReader.SampleRate, tailPadding);
s.InputFinished();
while (kws.IsReady(s))
{
kws.Decode(s);
var result = kws.GetResult(s);
if (result.Keyword != "")
{
Console.WriteLine("Detected: {0}", result.Keyword);
}
}
Console.WriteLine("----------Use pre-defined keywords + add a new keyword----------");
s = kws.CreateStream("y ǎn y uán @演员");
s.AcceptWaveform(waveReader.SampleRate, waveReader.Samples);
s.AcceptWaveform(waveReader.SampleRate, tailPadding);
s.InputFinished();
while (kws.IsReady(s))
{
kws.Decode(s);
var result = kws.GetResult(s);
if (result.Keyword != "")
{
Console.WriteLine("Detected: {0}", result.Keyword);
}
}
Console.WriteLine("----------Use pre-defined keywords + add 2 new keywords----------");
// Note keywords are separated by /
s = kws.CreateStream("y ǎn y uán @演员/zh ī m íng @知名");
s.AcceptWaveform(waveReader.SampleRate, waveReader.Samples);
s.AcceptWaveform(waveReader.SampleRate, tailPadding);
s.InputFinished();
while (kws.IsReady(s))
{
kws.Decode(s);
var result = kws.GetResult(s);
if (result.Keyword != "")
{
Console.WriteLine("Detected: {0}", result.Keyword);
}
}
}
}

View File

@@ -0,0 +1,15 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>Exe</OutputType>
<TargetFramework>net6.0</TargetFramework>
<RootNamespace>keyword_spotting_from_files</RootNamespace>
<ImplicitUsings>enable</ImplicitUsings>
<Nullable>enable</Nullable>
</PropertyGroup>
<ItemGroup>
<ProjectReference Include="..\Common\Common.csproj" />
</ItemGroup>
</Project>

View File

@@ -0,0 +1,11 @@
#!/usr/bin/env bash
set -ex
if [ ! -f ./sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01/tokens.txt ]; then
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/kws-models/sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
tar xvf sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
rm sherpa-onnx-kws-zipformer-wenetspeech-3.3M-2024-01-01.tar.bz2
fi
dotnet run -c Release

View File

@@ -22,7 +22,7 @@ fi
dotnet run -c Release \
--tokens ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/tokens.txt \
--encoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/encoder-epoch-99-avg-1.int8.onnx \
--decoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.int8.onnx \
--decoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.onnx \
--joiner ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/joiner-epoch-99-avg-1.int8.onnx \
--rule-fsts ./itn_zh_number.fst \
--decoding-method greedy_search \

View File

@@ -14,7 +14,7 @@ fi
dotnet run -c Release \
--tokens ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/tokens.txt \
--encoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/encoder-epoch-99-avg-1.int8.onnx \
--decoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.int8.onnx \
--decoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.onnx \
--joiner ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/joiner-epoch-99-avg-1.int8.onnx \
--decoding-method greedy_search \
--files ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/test_wavs/1.wav \

View File

@@ -25,6 +25,8 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "vad-non-streaming-asr-paraf
EndProject
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Common", "Common\Common.csproj", "{401E963F-E25A-43CE-987D-8DB2D4715756}"
EndProject
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "keyword-spotting-from-files", "keyword-spotting-from-files\keyword-spotting-from-files.csproj", "{A87EDD31-D654-4C9F-AED7-F6F2825659BD}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|Any CPU = Debug|Any CPU
@@ -75,6 +77,10 @@ Global
{401E963F-E25A-43CE-987D-8DB2D4715756}.Debug|Any CPU.Build.0 = Debug|Any CPU
{401E963F-E25A-43CE-987D-8DB2D4715756}.Release|Any CPU.ActiveCfg = Release|Any CPU
{401E963F-E25A-43CE-987D-8DB2D4715756}.Release|Any CPU.Build.0 = Release|Any CPU
{A87EDD31-D654-4C9F-AED7-F6F2825659BD}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
{A87EDD31-D654-4C9F-AED7-F6F2825659BD}.Debug|Any CPU.Build.0 = Debug|Any CPU
{A87EDD31-D654-4C9F-AED7-F6F2825659BD}.Release|Any CPU.ActiveCfg = Release|Any CPU
{A87EDD31-D654-4C9F-AED7-F6F2825659BD}.Release|Any CPU.Build.0 = Release|Any CPU
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE

View File

@@ -18,5 +18,5 @@ fi
dotnet run -c Release \
--tokens ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/tokens.txt \
--encoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/encoder-epoch-99-avg-1.int8.onnx \
--decoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.int8.onnx \
--decoder ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/decoder-epoch-99-avg-1.onnx \
--joiner ./sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20/joiner-epoch-99-avg-1.int8.onnx