LocalAI/backend/go/silero-vad/vad.go
Ettore Di Giacinto 98e5291afc
feat: refactor build process, drop embedded backends (#5875)
* feat: split remaining backends and drop embedded backends

- Drop silero-vad, huggingface, and stores backend from embedded
  binaries
- Refactor Makefile and Dockerfile to avoid building grpc backends
- Drop golang code that was used to embed backends
- Simplify building by using goreleaser

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(gallery): be specific with llama-cpp backend templates

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(docs): update

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(ci): minor fixes

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: drop all ffmpeg references

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: run protogen-go

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Always enable p2p mode

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Update gorelease file

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(stores): do not always load

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix linting issues

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Mac OS fixup

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-07-22 16:31:04 +02:00

58 lines
1.3 KiB
Go

package main
// This is a wrapper to statisfy the GRPC service interface
// It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
import (
"fmt"
"github.com/mudler/LocalAI/pkg/grpc/base"
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
"github.com/streamer45/silero-vad-go/speech"
)
type VAD struct {
base.SingleThread
detector *speech.Detector
}
func (vad *VAD) Load(opts *pb.ModelOptions) error {
v, err := speech.NewDetector(speech.DetectorConfig{
ModelPath: opts.ModelFile,
SampleRate: 16000,
//WindowSize: 1024,
Threshold: 0.5,
MinSilenceDurationMs: 100,
SpeechPadMs: 30,
})
if err != nil {
return fmt.Errorf("create silero detector: %w", err)
}
vad.detector = v
return err
}
func (vad *VAD) VAD(req *pb.VADRequest) (pb.VADResponse, error) {
audio := req.Audio
if err := vad.detector.Reset(); err != nil {
return pb.VADResponse{}, fmt.Errorf("reset: %w", err)
}
segments, err := vad.detector.Detect(audio)
if err != nil {
return pb.VADResponse{}, fmt.Errorf("detect: %w", err)
}
vadSegments := []*pb.VADSegment{}
for _, s := range segments {
vadSegments = append(vadSegments, &pb.VADSegment{
Start: float32(s.SpeechStartAt),
End: float32(s.SpeechEndAt),
})
}
return pb.VADResponse{
Segments: vadSegments,
}, nil
}