feat(silero): add Silero-vad backend (#4204)

* feat(vad): add silero-vad backend (WIP)

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

* feat(vad): add API endpoint

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

* fix(vad): correctly place the onnxruntime libs

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

* chore(vad): hook silero-vad to binary and container builds

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

* feat(gRPC): register VAD Server

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

* fix(Makefile): consume ONNX_OS consistently

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

* fix(Makefile): handle macOS

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Ettore Di Giacinto 2024-11-20 14:48:40 +01:00 committed by GitHub
parent 9892d7d584
commit b1ea9318e6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 255 additions and 1 deletions

View file

@ -28,6 +28,8 @@ service Backend {
rpc Rerank(RerankRequest) returns (RerankResult) {}
rpc GetMetrics(MetricsRequest) returns (MetricsResponse);
rpc VAD(VADRequest) returns (VADResponse) {}
}
// Define the empty request
@ -293,6 +295,19 @@ message TTSRequest {
optional string language = 5;
}
message VADRequest {
repeated float audio = 1;
}
message VADSegment {
float start = 1;
float end = 2;
}
message VADResponse {
repeated VADSegment segments = 1;
}
message SoundGenerationRequest {
string text = 1;
string model = 2;