mathias/tapir
1
0
Fork 0
Code Issues 35 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(cmd): buildTranscriber -- the base-engine setting turns on the two-engine ensemble

Browse Source 
Default is the single-engine chain exactly as before. With TAPIR_RECONCILE_BASE_MODEL set,
the base engine and the primary run on the same WAV and a LOCAL model (config has already
refused any non-local alias) reconciles them, at temperature 0 with a short reply -- the
conditions its accuracy was measured under. The cloud fallback is unchanged and runs
only when both local engines fail.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
mathias
2026-10-01 23:26:02 +02:00
co-authored by Claude Sonnet 5.5
parent 7338d9d603
commit ed8ca54674
1 changed files with 40 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/tapir/uploads.go
+40 -10
View File
@@ -7,10 +7,13 @@ import (
"net/http"
"os"
"path/filepath"
"time"
"git.d-ma.be/mathias/tapir/internal/adapters/audio"
"git.d-ma.be/mathias/tapir/internal/adapters/llm"
"git.d-ma.be/mathias/tapir/internal/adapters/transcribe"
"git.d-ma.be/mathias/tapir/internal/config"
"git.d-ma.be/mathias/tapir/internal/reconcile"
"git.d-ma.be/mathias/tapir/internal/uploads"
"git.d-ma.be/mathias/tapir/internal/web"
)
@@ -52,16 +55,7 @@ func buildUploads(ctx context.Context, cfg config.Config, st uploadsStore, log *
log.Warn("uploads: marked interrupted by a restart (audio is not retained; they must be re-uploaded)", "count", n)
}
// No overall client timeout: a 90 minute recording takes minutes. The deadline
// is the worker's per-job context.
client := &http.Client{}
primary := transcribe.NewGateway(cfg.GatewayURL, cfg.GatewayKey, cfg.TranscribeModel, client)
var fallback transcribe.Backend
if cfg.TranscribeFallbackModel != "" && cfg.TranscribeFallbackModel != cfg.TranscribeModel {
fallback = transcribe.NewGateway(cfg.GatewayURL, cfg.GatewayKey, cfg.TranscribeFallbackModel, client)
}
worker := uploads.NewWorker(st, &audio.FFmpeg{Bin: cfg.FFmpegBin}, transcribe.NewChain(primary, fallback),
worker := uploads.NewWorker(st, &audio.FFmpeg{Bin: cfg.FFmpegBin}, buildTranscriber(cfg),
cfg.UploadTmpDir, cfg.TranscribeTimeout)
intake := uploads.NewIntake(st, &audio.FFprobe{Bin: cfg.FFprobeBin}, worker,
uploadLimits(cfg), cfg.UploadTmpDir)
@@ -98,3 +92,39 @@ func wireUploads(app *web.App, cfg config.Config, in *uploads.Intake) {
app.UploadChatMaxChars = cfg.MaxUploadedTranscriptChars
app.UploadChatModel = cfg.UploadChatModel
}
// adjudicatorTimeout bounds one adjudication call. A call takes ~2 s on gemma4-26b and ~10 s
// on 31b; this is the wait before an unresponsive model is counted as an error.
const adjudicatorTimeout = 2 * time.Minute
// buildTranscriber builds what the worker transcribes with. By default that is the
// single-engine chain (the primary, then the optional cloud fallback). When
// TAPIR_RECONCILE_BASE_MODEL is set it is the two-engine ensemble (ADR-034): the base
// engine and the primary run on the same WAV and a LOCAL model reconciles them. Config
// has already refused any non-local model, so nothing here can send private audio or
// text to a cloud model for reconciliation; the cloud fallback is unchanged.
func buildTranscriber(cfg config.Config) uploads.Transcriber {
// No overall client timeout: a 90 minute recording takes minutes. The deadline is
// the worker's per-job context.
client := &http.Client{}
primary := transcribe.NewGateway(cfg.GatewayURL, cfg.GatewayKey, cfg.TranscribeModel, client)
var fallback transcribe.Backend
if cfg.TranscribeFallbackModel != "" && cfg.TranscribeFallbackModel != cfg.TranscribeModel {
fallback = transcribe.NewGateway(cfg.GatewayURL, cfg.GatewayKey, cfg.TranscribeFallbackModel, client)
}
if cfg.ReconcileBaseModel == "" {
return transcribe.NewChain(primary, fallback)
}
base := transcribe.NewGateway(cfg.GatewayURL, cfg.GatewayKey, cfg.ReconcileBaseModel, client)
// Temperature 0 and a short reply: the adjudicator's accuracy was measured that way.
chat := llm.New(cfg.GatewayURL, cfg.GatewayKey, cfg.ReconcileModel, adjudicatorTimeout,
llm.WithTemperature(0), llm.WithMaxTokens(200))
var adj reconcile.Adjudicator = reconcile.NewLLMAdjudicator(chat)
if cfg.ReconcileCheckOrder {
adj = reconcile.NewOrderChecked(adj)
}
return transcribe.NewEnsemble(base, primary, fallback, adj, reconcile.Options{
BaseEngine: cfg.ReconcileBaseModel, AltEngine: cfg.TranscribeModel, Reconciler: cfg.ReconcileModel,
})
}