Initial import

go.mod

@@ -0,0 +1,13 @@
+module github.com/go-skynet/whisper
+
+go 1.19
+
+require (
+	github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230307193630-09e90680072d
+	github.com/go-audio/wav v1.1.0
+)
+
+require (
+	github.com/go-audio/audio v1.0.0 // indirect
+	github.com/go-audio/riff v1.0.0 // indirect
+)

go.sum

@@ -0,0 +1,12 @@
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230307193630-09e90680072d h1:a+wrVgrr8EGpMmauel61hLJsM7h3LGXwoB2oUdPyr7Y=
+github.com/ggerganov/whisper.cpp/bindings/go v0.0.0-20230307193630-09e90680072d/go.mod h1:QIjZ9OktHFG7p+/m3sMvrAJKKdWrr1fZIK0rM6HZlyo=
+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/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

whisper.go

@@ -0,0 +1,79 @@
+package whisper
+
+import (
+	"fmt"
+	"os"
+	"os/exec"
+
+	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
+	wav "github.com/go-audio/wav"
+)
+
+func sh(c string) (string, error) {
+	cmd := exec.Command("/bin/sh", "-c", c)
+	cmd.Env = os.Environ()
+	o, err := cmd.CombinedOutput()
+	return string(o), err
+}
+
+// AudioToWav converts audio to wav for transcribe. It bashes out to ffmpeg
+// TODO: use https://github.com/mccoyst/ogg?
+func AudioToWav(src, dst string) error {
+	out, err := sh(fmt.Sprintf("ffmpeg -i %s -format s16le -ar 16000 -ac 1 -acodec pcm_s16le %s", src, dst))
+	if err != nil {
+		return fmt.Errorf("error: %w out: %s", err, out)
+	}
+
+	return nil
+}
+
+func Transcribe(modelpath, audiopath, language string) (string, error) {
+	// Open samples
+	fh, err := os.Open(audiopath)
+	if err != nil {
+		return "", err
+	}
+	defer fh.Close()
+
+	// Read samples
+	d := wav.NewDecoder(fh)
+	buf, err := d.FullPCMBuffer()
+	if err != nil {
+		return "", err
+	}
+
+	data := buf.AsFloat32Buffer().Data
+
+	// Load the model
+	model, err := whisper.New(modelpath)
+	if err != nil {
+		return "", err
+	}
+	defer model.Close()
+
+	// Process samples
+	context, err := model.NewContext()
+	if err != nil {
+		return "", err
+
+	}
+
+	if language != "" {
+		context.SetLanguage(language)
+	}
+
+	if err := context.Process(data, nil); err != nil {
+		return "", err
+	}
+
+	text := ""
+	for {
+		segment, err := context.NextSegment()
+		if err != nil {
+			break
+		}
+		text += segment.Text
+	}
+
+	return text, nil
+}