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

@ -30,10 +30,16 @@ type TTSRequest struct {
Input string `json:"input" yaml:"input"` // text input
Voice string `json:"voice" yaml:"voice"` // voice audio file or speaker id
Backend string `json:"backend" yaml:"backend"`
Language string `json:"language,omitempty" yaml:"language,omitempty"` // (optional) language to use with TTS model
Language string `json:"language,omitempty" yaml:"language,omitempty"` // (optional) language to use with TTS model
Format string `json:"response_format,omitempty" yaml:"response_format,omitempty"` // (optional) output format
}
// @Description VAD request body
type VADRequest struct {
Model string `json:"model" yaml:"model"` // model name or full path
Audio []float32 `json:"audio" yaml:"audio"` // model name or full path
}
type StoresSet struct {
Store string `json:"store,omitempty" yaml:"store,omitempty"`