Files
LocalAI/backend/go/voice-detect/main.go
T
mudler-agentandEttore Di Giacinto 6343a2dc6f feat(voice-detect): report the encoder family so audio-registered voices are fingerprinted (#12499)
* feat(voice-detect): report the encoder family so audio-registered voices are fingerprinted

A voice registered from audio through the voice-detect backend had no
encoder fingerprint, so the parakeet-cpp backend could not tell whether
it was comparable with the loaded speaker model and could only fall back
to the file-name rule.

The voice-detect backend now binds the three new libvoicedetect accessors
with a symbol probe (an older library still loads and reports nothing),
copies the borrowed strings at once and never frees them. It also hashes
the model file once at load. VoiceEmbedResponse gains two optional
fields, encoder_family and encoder_weights ("sha256:<hex>", empty when
the model is not a plain file).

/v1/voice/register stores them as encoder_family and a new
encoder_weights field in the registry entry; model keeps the encoder
name, so the 1:N identify filter by name is unchanged for old entries.
A voice with a family is sent to the backend whatever its file name, and
the backend decides by family. /v1/voice/identify compares the family
when both the stored voice and the probe have one. Old entries load
without the fields and stay unfingerprinted.

Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* docs(voice-detect): say how a voice with weights but no family is treated

Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(voice-detect): mark the model file open as intended for gosec

Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-10-08 19:26:11 +02:00

78 lines
2.4 KiB
Go

package main
// Started internally by LocalAI - one gRPC server per loaded model.
//
// Loads libvoicedetect.so via purego and registers the flat C-API entry points
// declared in voicedetect_capi.h. The library name can be overridden with
// VOICEDETECT_LIBRARY (mirrors the PARAKEET_LIBRARY / OMNIVOICE_LIBRARY
// convention in the sibling backends); the default looks for the .so next to
// this binary (resolved via LD_LIBRARY_PATH by run.sh).
import (
"flag"
"fmt"
"os"
"github.com/ebitengine/purego"
grpc "github.com/mudler/LocalAI/pkg/grpc"
)
var (
addr = flag.String("addr", "localhost:50051", "the address to connect to")
)
type LibFuncs struct {
FuncPtr any
Name string
}
func main() {
libName := os.Getenv("VOICEDETECT_LIBRARY")
if libName == "" {
libName = "libvoicedetect.so"
}
lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
if err != nil {
panic(fmt.Errorf("voice-detect: dlopen %q: %w", libName, err))
}
// Bound 1:1 to voicedetect_capi.h. char*/float* returns are registered as
// uintptr so the raw pointer can be freed via the matching capi free fn.
libFuncs := []LibFuncs{
{&CppAbiVersion, "voicedetect_capi_abi_version"},
{&CppLoad, "voicedetect_capi_load"},
{&CppFree, "voicedetect_capi_free"},
{&CppLastError, "voicedetect_capi_last_error"},
{&CppFreeString, "voicedetect_capi_free_string"},
{&CppFreeVec, "voicedetect_capi_free_vec"},
{&CppEmbedPath, "voicedetect_capi_embed_path"},
{&CppEmbedPCM, "voicedetect_capi_embed_pcm"},
{&CppVerifyPaths, "voicedetect_capi_verify_paths"},
{&CppAnalyzeJSON, "voicedetect_capi_analyze_path_json"},
}
for _, lf := range libFuncs {
purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
}
// Encoder identity accessors (additive in voice-detect.cpp, no ABI bump).
// Probed so a libvoicedetect.so from before them still loads: the encoder
// family then stays empty and audio-registered voices stay unfingerprinted.
for _, lf := range []LibFuncs{
{&CppEncoderArch, "voicedetect_capi_encoder_arch"},
{&CppEncoderName, "voicedetect_capi_encoder_name"},
{&CppEncoderFamily, "voicedetect_capi_encoder_family"},
} {
if sym, err := purego.Dlsym(lib, lf.Name); err == nil && sym != 0 {
purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
}
}
fmt.Fprintf(os.Stderr, "[voice-detect] ABI=%d\n", CppAbiVersion())
flag.Parse()
if err := grpc.StartServer(*addr, &VoiceDetect{}); err != nil {
panic(err)
}
}