Back to corpus
architecturetechnical paper candidatescore 44

N'Ko Intelligence Pipeline — Full Architecture

┌─────────────┐ ┌──────────────┐ ┌──────────────┐ ┌───────────────┐ │ bam-asr- │ │ AfVoices │ │ Djoko │ │ Parents' │ │ early │ │ 253K audio │ │ YouTube │ │ Voice Memos │ │ 38K clean │ │ Latin text │ │ 5.5K audio │ │ Malinke │ │ N'Ko labels │ │ NO N'Ko │ │ consensus │ │ diarized │ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ └───────┬───────┘ │ │ │ │ │ ┌────────┴────────┐ │ │ │ │ NEEDS TONE-AWARE│ │ │ │ │ TRANSLITERATION │ │ │ │ │ (blocked until │ │ │ │ │ tone model) │ │ │ │ └────────┬────────┘ │ │ │ │ │ │ ▼ ▼ ▼

Open full HTMLDownload HTMLCorpus JSONPaper schema

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

| Component | Status | Next Action | |-----------|--------|-------------| | 44K clean data | READY | Training TAR now | | 253K AfVoices features | EXTRACTED | Waiting for tone model | | N'Ko trajectory CER | 27.39% (297K) | Retrain on 44K clean queued | | TAR experiment | TRAINING | 4 runs on A100 | | ANE spike | 11.6 TFLOPS proven | Wire into training loop | | YouTube OCR (Gemma 4) | QUEUED | Task #31 on Vast.ai | | Tone resolution model | PLANNED | Depends on OCR corpus | | TurboQuant | BUILT | Needs real embedding test | | Contextual tone paper | PLANNED | Depends on OCR + tone model | | ANE distributed paper | PLANNED | Depends on training loop proof |

Promotion decision

What has to happen next

Promote into a technical note or architecture paper with implementation anchors.

Why this is not always a full paper yet

Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.