-
-
Notifications
You must be signed in to change notification settings - Fork 2.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat(silero): add Silero-vad backend (#4204)
* feat(vad): add silero-vad backend (WIP) Signed-off-by: Ettore Di Giacinto <[email protected]> * feat(vad): add API endpoint Signed-off-by: Ettore Di Giacinto <[email protected]> * fix(vad): correctly place the onnxruntime libs Signed-off-by: Ettore Di Giacinto <[email protected]> * chore(vad): hook silero-vad to binary and container builds Signed-off-by: Ettore Di Giacinto <[email protected]> * feat(gRPC): register VAD Server Signed-off-by: Ettore Di Giacinto <[email protected]> * fix(Makefile): consume ONNX_OS consistently Signed-off-by: Ettore Di Giacinto <[email protected]> * fix(Makefile): handle macOS Signed-off-by: Ettore Di Giacinto <[email protected]> --------- Signed-off-by: Ettore Di Giacinto <[email protected]> Signed-off-by: Ettore Di Giacinto <[email protected]>
- Loading branch information
Showing
15 changed files
with
255 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,21 @@ | ||
| package main | ||
|
|
||
| // Note: this is started internally by LocalAI and a server is allocated for each model | ||
|
|
||
| import ( | ||
| "flag" | ||
|
|
||
| grpc "github.com/mudler/LocalAI/pkg/grpc" | ||
| ) | ||
|
|
||
| var ( | ||
| addr = flag.String("addr", "localhost:50051", "the address to connect to") | ||
| ) | ||
|
|
||
| func main() { | ||
| flag.Parse() | ||
|
|
||
| if err := grpc.StartServer(*addr, &VAD{}); err != nil { | ||
| panic(err) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,54 @@ | ||
| 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: 0, | ||
| SpeechPadMs: 0, | ||
| }) | ||
| 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 | ||
|
|
||
| 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 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,68 @@ | ||
| package localai | ||
|
|
||
| import ( | ||
| "github.com/gofiber/fiber/v2" | ||
| "github.com/mudler/LocalAI/core/backend" | ||
| "github.com/mudler/LocalAI/core/config" | ||
| fiberContext "github.com/mudler/LocalAI/core/http/ctx" | ||
| "github.com/mudler/LocalAI/core/schema" | ||
| "github.com/mudler/LocalAI/pkg/grpc/proto" | ||
| "github.com/mudler/LocalAI/pkg/model" | ||
| "github.com/rs/zerolog/log" | ||
| ) | ||
|
|
||
| // VADEndpoint is Voice-Activation-Detection endpoint | ||
| // @Summary Detect voice fragments in an audio stream | ||
| // @Accept json | ||
| // @Param request body schema.VADRequest true "query params" | ||
| // @Success 200 {object} proto.VADResponse "Response" | ||
| // @Router /vad [post] | ||
| func VADEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error { | ||
| return func(c *fiber.Ctx) error { | ||
|
|
||
| input := new(schema.VADRequest) | ||
|
|
||
| // Get input data from the request body | ||
| if err := c.BodyParser(input); err != nil { | ||
| return err | ||
| } | ||
|
|
||
| modelFile, err := fiberContext.ModelFromContext(c, cl, ml, input.Model, false) | ||
| if err != nil { | ||
| modelFile = input.Model | ||
| log.Warn().Msgf("Model not found in context: %s", input.Model) | ||
| } | ||
|
|
||
| cfg, err := cl.LoadBackendConfigFileByName(modelFile, appConfig.ModelPath, | ||
| config.LoadOptionDebug(appConfig.Debug), | ||
| config.LoadOptionThreads(appConfig.Threads), | ||
| config.LoadOptionContextSize(appConfig.ContextSize), | ||
| config.LoadOptionF16(appConfig.F16), | ||
| ) | ||
|
|
||
| if err != nil { | ||
| log.Err(err) | ||
| modelFile = input.Model | ||
| log.Warn().Msgf("Model not found in context: %s", input.Model) | ||
| } else { | ||
| modelFile = cfg.Model | ||
| } | ||
| log.Debug().Msgf("Request for model: %s", modelFile) | ||
|
|
||
| opts := backend.ModelOptions(*cfg, appConfig, model.WithBackendString(cfg.Backend), model.WithModel(modelFile)) | ||
|
|
||
| vadModel, err := ml.Load(opts...) | ||
| if err != nil { | ||
| return err | ||
| } | ||
| req := proto.VADRequest{ | ||
| Audio: input.Audio, | ||
| } | ||
| resp, err := vadModel.VAD(c.Context(), &req) | ||
| if err != nil { | ||
| return err | ||
| } | ||
|
|
||
| return c.JSON(resp) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters