mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 04:56:52 -04:00
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>
139 lines
3.4 KiB
Go
139 lines
3.4 KiB
Go
package trace
|
|
|
|
import (
|
|
"encoding/json"
|
|
"slices"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/emirpasic/gods/v2/queues/circularbuffer"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
type BackendTraceType string
|
|
|
|
const (
|
|
BackendTraceLLM BackendTraceType = "llm"
|
|
BackendTraceEmbedding BackendTraceType = "embedding"
|
|
BackendTraceTranscription BackendTraceType = "transcription"
|
|
BackendTraceImageGeneration BackendTraceType = "image_generation"
|
|
BackendTraceVideoGeneration BackendTraceType = "video_generation"
|
|
BackendTraceTTS BackendTraceType = "tts"
|
|
BackendTraceSoundGeneration BackendTraceType = "sound_generation"
|
|
BackendTraceRerank BackendTraceType = "rerank"
|
|
BackendTraceTokenize BackendTraceType = "tokenize"
|
|
BackendTraceDetection BackendTraceType = "detection"
|
|
BackendTraceFaceVerify BackendTraceType = "face_verify"
|
|
BackendTraceFaceAnalyze BackendTraceType = "face_analyze"
|
|
BackendTraceVoiceVerify BackendTraceType = "voice_verify"
|
|
BackendTraceVoiceAnalyze BackendTraceType = "voice_analyze"
|
|
BackendTraceVoiceEmbed BackendTraceType = "voice_embed"
|
|
BackendTraceAudioTransform BackendTraceType = "audio_transform"
|
|
BackendTraceModelLoad BackendTraceType = "model_load"
|
|
)
|
|
|
|
type BackendTrace struct {
|
|
Timestamp time.Time `json:"timestamp"`
|
|
Duration time.Duration `json:"duration"`
|
|
Type BackendTraceType `json:"type"`
|
|
ModelName string `json:"model_name"`
|
|
Backend string `json:"backend"`
|
|
Summary string `json:"summary"`
|
|
Error string `json:"error,omitempty"`
|
|
Data map[string]any `json:"data"`
|
|
}
|
|
|
|
var backendTraceBuffer *circularbuffer.Queue[*BackendTrace]
|
|
var backendMu sync.Mutex
|
|
var backendLogChan = make(chan *BackendTrace, 100)
|
|
var backendInitOnce sync.Once
|
|
|
|
func InitBackendTracingIfEnabled(maxItems int) {
|
|
backendInitOnce.Do(func() {
|
|
if maxItems <= 0 {
|
|
maxItems = 100
|
|
}
|
|
backendMu.Lock()
|
|
backendTraceBuffer = circularbuffer.New[*BackendTrace](maxItems)
|
|
backendMu.Unlock()
|
|
|
|
go func() {
|
|
for t := range backendLogChan {
|
|
backendMu.Lock()
|
|
if backendTraceBuffer != nil {
|
|
backendTraceBuffer.Enqueue(t)
|
|
}
|
|
backendMu.Unlock()
|
|
}
|
|
}()
|
|
})
|
|
}
|
|
|
|
func RecordBackendTrace(t BackendTrace) {
|
|
select {
|
|
case backendLogChan <- &t:
|
|
default:
|
|
xlog.Warn("Backend trace channel full, dropping trace")
|
|
}
|
|
}
|
|
|
|
func GetBackendTraces() []BackendTrace {
|
|
backendMu.Lock()
|
|
if backendTraceBuffer == nil {
|
|
backendMu.Unlock()
|
|
return []BackendTrace{}
|
|
}
|
|
ptrs := backendTraceBuffer.Values()
|
|
backendMu.Unlock()
|
|
|
|
traces := make([]BackendTrace, len(ptrs))
|
|
for i, p := range ptrs {
|
|
traces[i] = *p
|
|
}
|
|
|
|
slices.SortFunc(traces, func(a, b BackendTrace) int {
|
|
return b.Timestamp.Compare(a.Timestamp)
|
|
})
|
|
|
|
return traces
|
|
}
|
|
|
|
func ClearBackendTraces() {
|
|
backendMu.Lock()
|
|
if backendTraceBuffer != nil {
|
|
backendTraceBuffer.Clear()
|
|
}
|
|
backendMu.Unlock()
|
|
}
|
|
|
|
func GenerateLLMSummary(messages schema.Messages, prompt string) string {
|
|
if len(messages) > 0 {
|
|
last := messages[len(messages)-1]
|
|
text := ""
|
|
switch content := last.Content.(type) {
|
|
case string:
|
|
text = content
|
|
default:
|
|
b, err := json.Marshal(content)
|
|
if err == nil {
|
|
text = string(b)
|
|
}
|
|
}
|
|
if text != "" {
|
|
return TruncateString(text, 200)
|
|
}
|
|
}
|
|
if prompt != "" {
|
|
return TruncateString(prompt, 200)
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func TruncateString(s string, maxLen int) string {
|
|
if len(s) <= maxLen {
|
|
return s
|
|
}
|
|
return s[:maxLen] + "..."
|
|
}
|