mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 04:56:52 -04:00
bb033b16a9
feat(audio-transform): add LocalVQE backend, bidi gRPC RPC, Studio UI
Introduce a generic "audio transform" capability for any audio-in / audio-out
operation (echo cancellation, noise suppression, dereverberation, voice
conversion, etc.) and ship LocalVQE as the first backend implementation.
Backend protocol:
- Two new gRPC RPCs in backend.proto: unary AudioTransform for batch and
bidirectional AudioTransformStream for low-latency frame-by-frame use.
This is the first bidi stream in the proto; per-frame unary at LocalVQE's
16 ms hop would be RTT-bound. Wire it through pkg/grpc/{client,server,
embed,interface,base} with paired-channel ergonomics.
LocalVQE backend (backend/go/localvqe/):
- Go-Purego wrapper around upstream liblocalvqe.so. CMake builds the upstream
shared lib + its libggml-cpu-*.so runtime variants directly — no MODULE
wrapper needed because LocalVQE handles CPU feature selection internally
via GGML_BACKEND_DL.
- Sets GGML_NTHREADS from opts.Threads (or runtime.NumCPU()-1) — without it
LocalVQE runs single-threaded at ~1× realtime instead of the documented
~9.6×.
- Reference-length policy: zero-pad short refs, truncate long ones (the
trailing portion can't have leaked into a mic that wasn't recording).
- Ginkgo test suite (9 always-on specs + 2 model-gated).
HTTP layer:
- POST /audio/transformations (alias /audio/transform): multipart batch
endpoint, accepts audio + optional reference + params[*]=v form fields.
Persists inputs alongside the output in GeneratedContentDir/audio so the
React UI history can replay past (audio, reference, output) triples.
- GET /audio/transformations/stream: WebSocket bidi, 16 ms PCM frames
(interleaved stereo mic+ref in, mono out). JSON session.update envelope
for config; constants hoisted in core/schema/audio_transform.go.
- ffmpeg-based input normalisation to 16 kHz mono s16 WAV via the existing
utils.AudioToWav (with passthrough fast-path), so the user can upload any
format / rate without seeing the model's strict 16 kHz constraint.
- BackendTraceAudioTransform integration so /api/backend-traces and the
Traces UI light up with audio_snippet base64 and timing.
- Routes registered under routes/localai.go (LocalAI extension; OpenAI has
no /audio/transformations endpoint), traced via TraceMiddleware.
Auth + capability + importer:
- FLAG_AUDIO_TRANSFORM (model_config.go), FeatureAudioTransform (default-on,
in APIFeatures), three RouteFeatureRegistry rows.
- localvqe added to knownPrefOnlyBackends with modality "audio-transform".
- Gallery entry localvqe-v1-1.3m (sha256-pinned, hosted on
huggingface.co/LocalAI-io/LocalVQE).
React UI:
- New /app/transform page surfaced via a dedicated "Enhance" sidebar
section (sibling of Tools / Biometrics) — the page is enhancement, not
generation, so it lives outside Studio. Two AudioInput components
(Upload + Record tabs, drag-drop, mic capture).
- Echo-test button: records mic while playing the loaded reference through
the speakers — the mic naturally picks up speaker bleed, giving a real
(mic, ref) pair for AEC testing without leaving the UI.
- Reusable WaveformPlayer (canvas peaks + click-to-seek + audio controls)
and useAudioPeaks hook (shared module-scoped AudioContext to avoid
hitting browser context limits with three players on one page); migrated
TTS, Sound, Traces audio blocks to use it.
- Past runs saved in localStorage via useMediaHistory('audio-transform') —
the history entry stores all three URLs so clicking re-renders the full
triple, not just the output.
Build + e2e:
- 11 matrix entries removed from .github/workflows/backend.yml (CUDA, ROCm,
SYCL, Metal, L4T): upstream supports only CPU + Vulkan, so we ship those
two and let GPU-class hardware route through Vulkan in the gallery
capabilities map.
- tests-localvqe-grpc-transform job in test-extra.yml (gated on
detect-changes.outputs.localvqe).
- New audio_transform capability + 4 specs in tests/e2e-backends.
- Playwright spec suite in core/http/react-ui/e2e/audio-transform.spec.js
(8 specs covering tabs, file upload, multipart shape, history, errors).
Docs:
- New docs/content/features/audio-transform.md covering the (audio,
reference) mental model, batch + WebSocket wire formats, LocalVQE param
keys, and a YAML config example. Cross-links from text-to-audio and
audio-to-text feature pages.
Assisted-by: Claude:claude-opus-4-7 [Bash Read Edit Write Agent TaskCreate]
Signed-off-by: Richard Palethorpe <io@richiejp.com>
101 lines
5.6 KiB
Go
101 lines
5.6 KiB
Go
package grpc
|
|
|
|
import (
|
|
"context"
|
|
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
"google.golang.org/grpc"
|
|
)
|
|
|
|
var embeds = map[string]*embedBackend{}
|
|
|
|
func Provide(addr string, llm AIModel) {
|
|
embeds[addr] = &embedBackend{s: &server{llm: llm}}
|
|
}
|
|
|
|
func NewClient(address string, parallel bool, wd WatchDog, enableWatchDog bool) Backend {
|
|
if bc, ok := embeds[address]; ok {
|
|
return bc
|
|
}
|
|
return buildClient(address, parallel, wd, enableWatchDog, "")
|
|
}
|
|
|
|
// NewClientWithToken creates a gRPC client that sends a bearer token with every call.
|
|
// Used in distributed mode to authenticate with remote backend processes.
|
|
func NewClientWithToken(address string, parallel bool, wd WatchDog, enableWatchDog bool, token string) Backend {
|
|
if bc, ok := embeds[address]; ok {
|
|
return bc
|
|
}
|
|
return buildClient(address, parallel, wd, enableWatchDog, token)
|
|
}
|
|
|
|
func buildClient(address string, parallel bool, wd WatchDog, enableWatchDog bool, token string) Backend {
|
|
if !enableWatchDog {
|
|
wd = nil
|
|
}
|
|
return &Client{
|
|
address: address,
|
|
parallel: parallel,
|
|
wd: wd,
|
|
token: token,
|
|
}
|
|
}
|
|
|
|
type Backend interface {
|
|
IsBusy() bool
|
|
HealthCheck(ctx context.Context) (bool, error)
|
|
Embeddings(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.EmbeddingResult, error)
|
|
LoadModel(ctx context.Context, in *pb.ModelOptions, opts ...grpc.CallOption) (*pb.Result, error)
|
|
PredictStream(ctx context.Context, in *pb.PredictOptions, f func(reply *pb.Reply), opts ...grpc.CallOption) error
|
|
Predict(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.Reply, error)
|
|
GenerateImage(ctx context.Context, in *pb.GenerateImageRequest, opts ...grpc.CallOption) (*pb.Result, error)
|
|
GenerateVideo(ctx context.Context, in *pb.GenerateVideoRequest, opts ...grpc.CallOption) (*pb.Result, error)
|
|
TTS(ctx context.Context, in *pb.TTSRequest, opts ...grpc.CallOption) (*pb.Result, error)
|
|
TTSStream(ctx context.Context, in *pb.TTSRequest, f func(reply *pb.Reply), opts ...grpc.CallOption) error
|
|
SoundGeneration(ctx context.Context, in *pb.SoundGenerationRequest, opts ...grpc.CallOption) (*pb.Result, error)
|
|
Detect(ctx context.Context, in *pb.DetectOptions, opts ...grpc.CallOption) (*pb.DetectResponse, error)
|
|
FaceVerify(ctx context.Context, in *pb.FaceVerifyRequest, opts ...grpc.CallOption) (*pb.FaceVerifyResponse, error)
|
|
FaceAnalyze(ctx context.Context, in *pb.FaceAnalyzeRequest, opts ...grpc.CallOption) (*pb.FaceAnalyzeResponse, error)
|
|
VoiceVerify(ctx context.Context, in *pb.VoiceVerifyRequest, opts ...grpc.CallOption) (*pb.VoiceVerifyResponse, error)
|
|
VoiceAnalyze(ctx context.Context, in *pb.VoiceAnalyzeRequest, opts ...grpc.CallOption) (*pb.VoiceAnalyzeResponse, error)
|
|
VoiceEmbed(ctx context.Context, in *pb.VoiceEmbedRequest, opts ...grpc.CallOption) (*pb.VoiceEmbedResponse, error)
|
|
AudioTranscription(ctx context.Context, in *pb.TranscriptRequest, opts ...grpc.CallOption) (*pb.TranscriptResult, error)
|
|
AudioTranscriptionStream(ctx context.Context, in *pb.TranscriptRequest, f func(chunk *pb.TranscriptStreamResponse), opts ...grpc.CallOption) error
|
|
TokenizeString(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.TokenizationResponse, error)
|
|
Status(ctx context.Context) (*pb.StatusResponse, error)
|
|
|
|
StoresSet(ctx context.Context, in *pb.StoresSetOptions, opts ...grpc.CallOption) (*pb.Result, error)
|
|
StoresDelete(ctx context.Context, in *pb.StoresDeleteOptions, opts ...grpc.CallOption) (*pb.Result, error)
|
|
StoresGet(ctx context.Context, in *pb.StoresGetOptions, opts ...grpc.CallOption) (*pb.StoresGetResult, error)
|
|
StoresFind(ctx context.Context, in *pb.StoresFindOptions, opts ...grpc.CallOption) (*pb.StoresFindResult, error)
|
|
|
|
Rerank(ctx context.Context, in *pb.RerankRequest, opts ...grpc.CallOption) (*pb.RerankResult, error)
|
|
|
|
GetTokenMetrics(ctx context.Context, in *pb.MetricsRequest, opts ...grpc.CallOption) (*pb.MetricsResponse, error)
|
|
|
|
VAD(ctx context.Context, in *pb.VADRequest, opts ...grpc.CallOption) (*pb.VADResponse, error)
|
|
|
|
AudioEncode(ctx context.Context, in *pb.AudioEncodeRequest, opts ...grpc.CallOption) (*pb.AudioEncodeResult, error)
|
|
AudioDecode(ctx context.Context, in *pb.AudioDecodeRequest, opts ...grpc.CallOption) (*pb.AudioDecodeResult, error)
|
|
|
|
AudioTransform(ctx context.Context, in *pb.AudioTransformRequest, opts ...grpc.CallOption) (*pb.AudioTransformResult, error)
|
|
AudioTransformStream(ctx context.Context, opts ...grpc.CallOption) (AudioTransformStreamClient, error)
|
|
|
|
ModelMetadata(ctx context.Context, in *pb.ModelOptions, opts ...grpc.CallOption) (*pb.ModelMetadataResponse, error)
|
|
|
|
// Fine-tuning
|
|
StartFineTune(ctx context.Context, in *pb.FineTuneRequest, opts ...grpc.CallOption) (*pb.FineTuneJobResult, error)
|
|
FineTuneProgress(ctx context.Context, in *pb.FineTuneProgressRequest, f func(update *pb.FineTuneProgressUpdate), opts ...grpc.CallOption) error
|
|
StopFineTune(ctx context.Context, in *pb.FineTuneStopRequest, opts ...grpc.CallOption) (*pb.Result, error)
|
|
ListCheckpoints(ctx context.Context, in *pb.ListCheckpointsRequest, opts ...grpc.CallOption) (*pb.ListCheckpointsResponse, error)
|
|
ExportModel(ctx context.Context, in *pb.ExportModelRequest, opts ...grpc.CallOption) (*pb.Result, error)
|
|
|
|
// Quantization
|
|
StartQuantization(ctx context.Context, in *pb.QuantizationRequest, opts ...grpc.CallOption) (*pb.QuantizationJobResult, error)
|
|
QuantizationProgress(ctx context.Context, in *pb.QuantizationProgressRequest, f func(update *pb.QuantizationProgressUpdate), opts ...grpc.CallOption) error
|
|
StopQuantization(ctx context.Context, in *pb.QuantizationStopRequest, opts ...grpc.CallOption) (*pb.Result, error)
|
|
|
|
// Free releases GPU/model resources (e.g. VRAM) without stopping the process.
|
|
Free(ctx context.Context) error
|
|
}
|