Files
LocalAI/core/cli/transcript.go
LocalAI [bot] 2be07f61da feat(whisper): honor client cancellation via ggml abort_callback (#9710)
* refactor(transcription): propagate request ctx through ModelTranscription*

Replaces context.Background() with the HTTP request ctx so client
disconnects start cancelling the gRPC call. No backend-side abort wiring
yet — that comes in a later commit. Pure plumbing.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(cli): pass ctx to backend.ModelTranscription

Follow-up to e65d3e1f which threaded ctx through ModelTranscription
but missed the CLI caller. CLI commands have no request-scoped ctx,
so context.Background() is correct here.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(audio): propagate request ctx into TTS, sound-gen, audio-transform

Same ctx-plumbing pattern applied to the rest of the audio path. CLI
callers use context.Background() since there is no request scope; HTTP
callers use c.Request().Context().

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(backend): propagate request ctx into biometric, detection, rerank, diarization paths

Replaces remaining context.Background() sites in core/backend with the
caller's ctx. After this commit, every core/backend/*.go entry point
threads the request ctx end-to-end to the gRPC client.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(grpc): plumb ctx through AIModel.AudioTranscription{,Stream}

Adds context.Context as first parameter to the AIModel interface methods
that wrap whisper-style transcription. Server-side gRPC handler now
forwards the per-RPC ctx (server-streaming uses stream.Context()).
Whisper, Voxtral, vibevoice-cpp, and sherpa-onnx accept the parameter;
none uses it yet — the actual cancellation primitive lands in the next
commit so this is pure plumbing.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): add abort_callback hook in the C++ bridge

Installs a std::atomic<int> flag, wires it into
whisper_full_params.abort_callback, and exposes a set_abort(int) C
symbol so Go can flip the flag from a goroutine watching the request
context. transcribe() now distinguishes abort (return 2) from real
whisper_full failure (return 1).

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): register set_abort symbol in the purego loader

Adds the Go-side binding for the new C export so the next commit can
call CppSetAbort(1) from a watcher goroutine on ctx.Done().

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): honor ctx cancellation and return codes.Canceled

A watcher goroutine watches ctx.Done() during AudioTranscription and
calls CppSetAbort(1) on cancel. whisper_full sees abort_callback return
true at the next compute graph step, returns non-zero, and the bridge
returns 2 -> AudioTranscription maps that to codes.Canceled.

Adds an opt-in test (gated on WHISPER_MODEL_PATH / WHISPER_AUDIO_PATH)
that asserts cancellation latency under 5s and proves the abort flag
resets cleanly so the next transcription succeeds.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(whisper): join the cancel watcher goroutine before returning

Follow-up to 85edf9d2. The previous commit used `defer close(done)` and
called the watcher "joined synchronously" — but close() only signals,
it does not block until the goroutine exits. That left a window where
a late CppSetAbort(1) from a cancelled call could land on the next
call, after its C-side g_abort reset but before whisper_full() began
polling the abort callback, corrupting the second transcription.

Switch to a sync.WaitGroup join so wg.Wait() blocks until the watcher
has actually returned from its select.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(whisper): short-circuit pre-cancelled ctx in AudioTranscription

If ctx is already Done() at entry, return codes.Canceled immediately
instead of running the full transcription. The C-side g_abort reset
happens at the start of transcribe() and would otherwise overwrite a
watcher-set abort flag from an already-cancelled ctx, producing a
spurious successful transcription on a request the client has already
abandoned.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(tests/distributed): update testLLM mock for new AudioTranscription signature

Phase B (93c48e19) added context.Context to AIModel.AudioTranscription
but missed the testLLM mock in tests/e2e/distributed. CI golangci-lint
caught it: *testLLM did not implement grpc.AIModel because the method
signature lacked the ctx parameter, which broke the distributed test
suite compilation and cascaded through every backend-build job that
runs `go build ./...`.

Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test(whisper): port cancellation test to Ginkgo/Gomega

Project policy (.agents/coding-style.md, enforced by golangci-lint
forbidigo) is that all Go tests must use Ginkgo v2 + Gomega — no
stdlib testing patterns (t.Skip, t.Fatalf, etc.). Convert the
cancellation test to a Describe/It block with Skip(...) for env
gating and Expect/HaveOccurred for assertions.

Same coverage: cancel mid-flight returns codes.Canceled within 5s and
a follow-up transcription succeeds, proving the C-side g_abort flag
resets cleanly.

Assisted-by: Claude:claude-opus-4-7
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>
2026-05-08 01:44:47 +02:00

138 lines
5.1 KiB
Go

package cli
import (
"context"
"encoding/json"
"fmt"
"strings"
"github.com/mudler/LocalAI/core/backend"
cliContext "github.com/mudler/LocalAI/core/cli/context"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/core/schema"
"github.com/mudler/LocalAI/pkg/model"
"github.com/mudler/LocalAI/pkg/system"
"github.com/mudler/xlog"
)
type TranscriptCMD struct {
Filename string `arg:"" name:"file" help:"Audio file to transcribe" type:"path"`
Backend string `short:"b" default:"whisper" help:"Backend to run the transcription model"`
Model string `short:"m" required:"" help:"Model name to run the TTS"`
Language string `short:"l" help:"Language of the audio file"`
Translate bool `short:"c" help:"Translate the transcription to English"`
Diarize bool `short:"d" help:"Mark speaker turns"`
Threads int `short:"t" default:"1" help:"Number of threads used for parallel computation"`
BackendsPath string `env:"LOCALAI_BACKENDS_PATH,BACKENDS_PATH" type:"path" default:"${basepath}/backends" help:"Path containing backends used for inferencing" group:"storage"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendGalleries string `env:"LOCALAI_BACKEND_GALLERIES,BACKEND_GALLERIES" help:"JSON list of backend galleries" group:"backends" default:"${backends}"`
Prompt string `short:"p" help:"Previous transcribed text or words that hint at what the model should expect"`
ResponseFormat schema.TranscriptionResponseFormatType `short:"f" default:"" help:"Response format for Whisper models, can be one of (txt, lrc, srt, vtt, json, verbose_json)"`
PrettyPrint bool `help:"Used with response_format json or verbose_json for pretty printing"`
}
func (t *TranscriptCMD) Run(ctx *cliContext.Context) error {
systemState, err := system.GetSystemState(
system.WithBackendPath(t.BackendsPath),
system.WithModelPath(t.ModelsPath),
)
if err != nil {
return err
}
opts := &config.ApplicationConfig{
SystemState: systemState,
Context: context.Background(),
}
cl := config.NewModelConfigLoader(t.ModelsPath)
ml := model.NewModelLoader(systemState)
if err := gallery.RegisterBackends(systemState, ml); err != nil {
xlog.Error("error registering external backends", "error", err)
}
if err := cl.LoadModelConfigsFromPath(t.ModelsPath); err != nil {
return err
}
c, exists := cl.GetModelConfig(t.Model)
if !exists {
return fmt.Errorf("model %q not found. Run 'local-ai models list' to see available models, or install one with 'local-ai models install <model>'. See https://localai.io/models/ for more information", t.Model)
}
c.Threads = &t.Threads
defer func() {
err := ml.StopAllGRPC()
if err != nil {
xlog.Error("unable to stop all grpc processes", "error", err)
}
}()
tr, err := backend.ModelTranscription(context.Background(), t.Filename, t.Language, t.Translate, t.Diarize, t.Prompt, ml, c, opts)
if err != nil {
return err
}
switch t.ResponseFormat {
case schema.TranscriptionResponseFormatLrc, schema.TranscriptionResponseFormatSrt, schema.TranscriptionResponseFormatVtt, schema.TranscriptionResponseFormatText:
fmt.Println(schema.TranscriptionResponse(tr, t.ResponseFormat))
case schema.TranscriptionResponseFormatJson:
tr.Segments = nil
tr.Words = nil
fallthrough
case schema.TranscriptionResponseFormatJsonVerbose:
trs := schema.TranscriptionResultSeconds{
Text: tr.Text,
Language: tr.Language,
Duration: tr.Duration,
Words: []schema.TranscriptionWordSeconds{},
Segments: []schema.TranscriptionSegmentSeconds{},
}
for _, word := range(tr.Words) {
trs.Words = append(trs.Words, schema.TranscriptionWordSeconds{
Start: word.Start.Seconds(),
End: word.End.Seconds(),
Text: word.Text,
})
}
for _, seg := range(tr.Segments) {
segWords := []schema.TranscriptionWordSeconds{}
for _, word := range(seg.Words) {
segWords = append(segWords, schema.TranscriptionWordSeconds{
Start: word.Start.Seconds(),
End: word.End.Seconds(),
Text: word.Text,
})
}
trs.Segments = append(trs.Segments, schema.TranscriptionSegmentSeconds{
Id: seg.Id,
Start: seg.Start.Seconds(),
End: seg.End.Seconds(),
Text: seg.Text,
Tokens: seg.Tokens,
Speaker: seg.Speaker,
Words: segWords,
})
}
var mtr []byte
var err error
if t.PrettyPrint {
mtr, err = json.MarshalIndent(trs, "", " ")
} else {
mtr, err = json.Marshal(trs)
}
if err != nil {
return err
}
fmt.Println(string(mtr))
default:
for _, segment := range tr.Segments {
fmt.Println(segment.Start.String(), "-", strings.TrimSpace(segment.Text))
}
}
return nil
}