update

Dockerfile

@@ -1,11 +1,11 @@
-FROM golang:1.18
+FROM golang:1.23
 
 WORKDIR /data/GolandProjects/vad_go
 
 COPY . /data/GolandProjects/vad_go
 
 RUN apt-get update
-RUN apt-get install -y python3-pip
+RUN apt-get install -y python3-pip onnxruntime
 
 RUN pip install --upgrade pip
 RUN pip install --no-cache-dir --upgrade -r /data/GolandProjects/vad_go/requirements.txt

build_vad_go.sh

@@ -3,9 +3,13 @@
 mkdir -p vad_bins/
 
 # nx_vad
-
 cd nx_vad
-
 bash build_nx_vad.sh
-
 cp ./build/nx_vad ../vad_bins/nx_vad
+cd ..
+
+# silero
+cd silero
+bash build_silero_vad.sh
+cp ./build/silero ../vad_bins/silero
+cd ..

silero/build_silero_vad.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+
+mkdir build
+
+go env -w GO111MODULE=on
+go env GO111MODULE
+
+go mod init silero
+
+go mod tidy
+
+go build -o build silero

silero/go.mod

@@ -0,0 +1,13 @@
+module silero
+
+go 1.23.4
+
+require (
+	github.com/go-audio/wav v1.1.0
+	github.com/streamer45/silero-vad-go v0.2.1
+)
+
+require (
+	github.com/go-audio/audio v1.0.0 // indirect
+	github.com/go-audio/riff v1.0.0 // indirect
+)

silero/go.sum

@@ -0,0 +1,16 @@
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/go-audio/audio v1.0.0 h1:zS9vebldgbQqktK4H0lUqWrG8P0NxCJVqcj7ZpNnwd4=
+github.com/go-audio/audio v1.0.0/go.mod h1:6uAu0+H2lHkwdGsAY+j2wHPNPpPoeg5AaEFh9FlA+Zs=
+github.com/go-audio/riff v1.0.0 h1:d8iCGbDvox9BfLagY94fBynxSPHO80LmZCaOsmKxokA=
+github.com/go-audio/riff v1.0.0/go.mod h1:l3cQwc85y79NQFCRB7TiPoNiaijp6q8Z0Uv38rVG498=
+github.com/go-audio/wav v1.1.0 h1:jQgLtbqBzY7G+BM8fXF7AHUk1uHUviWS4X39d5rsL2g=
+github.com/go-audio/wav v1.1.0/go.mod h1:mpe9qfwbScEbkd8uybLuIpTgHyrISw/OTuvjUW2iGtE=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/streamer45/silero-vad-go v0.2.1 h1:Li1/tTC4H/3cyw6q4weX+U8GWwEL3lTekK/nYa1Cvuk=
+github.com/streamer45/silero-vad-go v0.2.1/go.mod h1:B+2FXs/5fZ6pzl6unUZYhZqkYdOB+3saBVzjOzdZnUs=
+github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
+github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

silero/main.go

@@ -0,0 +1,63 @@
+package main
+
+import (
+	"log"
+	"os"
+
+	"github.com/streamer45/silero-vad-go/speech"
+
+	"github.com/go-audio/wav"
+)
+
+func main() {
+	sd, err := speech.NewDetector(speech.DetectorConfig{
+		ModelPath:            "../../src/silero_vad/data/silero_vad.onnx",
+		SampleRate:           16000,
+		Threshold:            0.5,
+		MinSilenceDurationMs: 100,
+		SpeechPadMs:          30,
+	})
+	if err != nil {
+		log.Fatalf("failed to create speech detector: %s", err)
+	}
+
+	if len(os.Args) != 2 {
+		log.Fatalf("invalid arguments provided: expecting one file path")
+	}
+
+	f, err := os.Open(os.Args[1])
+	if err != nil {
+		log.Fatalf("failed to open sample audio file: %s", err)
+	}
+	defer f.Close()
+
+	dec := wav.NewDecoder(f)
+
+	if ok := dec.IsValidFile(); !ok {
+		log.Fatalf("invalid WAV file")
+	}
+
+	buf, err := dec.FullPCMBuffer()
+	if err != nil {
+		log.Fatalf("failed to get PCM buffer")
+	}
+
+	pcmBuf := buf.AsFloat32Buffer()
+
+	segments, err := sd.Detect(pcmBuf.Data)
+	if err != nil {
+		log.Fatalf("Detect failed: %s", err)
+	}
+
+	for _, s := range segments {
+		log.Printf("speech starts at %0.2fs", s.SpeechStartAt)
+		if s.SpeechEndAt > 0 {
+			log.Printf("speech ends at %0.2fs", s.SpeechEndAt)
+		}
+	}
+
+	err = sd.Destroy()
+	if err != nil {
+		log.Fatalf("failed to destroy detector: %s", err)
+	}
+}