{ "model_id": "baobab-twi", "display_name": "Baobab Twi", "model_version": "2026.10.deferred", "family": "baobab", "status": "deferred_slice_shipped", "product_line": "National Twi speech + MT corridor (phrase + optional NC NLLB) with Phase D generative research slot — generative_inference_live false; trainingEligible locked.", "varieties": [ { "variety_id": "ak-gh-asante", "pack_key": "asante", "name_en": "Asante Twi", "bcp47": "ak-GH", "echo_voice_id": "own:ak-gh-female", "english_accent": { "locale": "en-GH", "voice_id": "own:en-gh-female", "label": "Ama · Ghanaian English", "region": "ghana", "note": "Ghanaian English accent paired with Ghana L1 national models (Twi, Ga, Ewe, Fante, Hausa Zongo) and nearest West African English for Senegal / Côte d'Ivoire French nationals until dedicated en-SN / en-CI accents ship. Never substitutes for L1 French." }, "mt_lang_key": "ak", "language_pack_version": "asante-pack-2026.10-b", "corridor_id": "en-ak-asante", "primary_use": "Everyday / CS / MeetingBridge Ghana", "domains": [ "greetings", "public_services", "education", "health", "civic", "customer_support" ], "dataset_manifest": "apps/api/eval/baobab-twi/dataset-manifest.asante.json", "trainingEligible": false, "not_interchangeable_with": [ "ak-gh-akuapem", "ak-gh-akuapem-twi", "ak-gh-fante" ], "mt": { "status": "phrase_table_only", "pairs": [ "en↔ak" ], "phase_b_expanded": true, "note": "Phase B phrase + lexical pack. Fail-closed when uncovered. Neural NMT when BAOBAB_TWI_NMT_URL live." }, "asr": { "status": "neural_offline", "checkpoint": "tiffany101/whisper-twi-v2", "license": "Apache-2.0", "env_gate": "Asante speech", "variety_exclusive_finetune": false }, "tts": { "status": "neural_offline", "checkpoint": "onnx-community/mms-tts-aka-ONNX", "license": "CC-BY-NC-4.0", "env_gate": "Asante speech", "variety_exclusive_finetune": false }, "s2s_corridor": { "status": "corridor_pass", "note": "Corridor scripts PASS (en-GH TTS ↔ Baobab ↔ Asante TTS/ASR). Broad domain deferred." }, "speech_finetune_recipe": "docs/baobab/SPEECH_FINETUNE_RECIPE.md" }, { "variety_id": "ak-gh-akuapem", "pack_key": "akuapem", "name_en": "Akuapem Twi", "bcp47": "ak-GH", "echo_voice_id": "own:ak-gh-akuapem-female", "english_accent": { "locale": "en-GH", "voice_id": "own:en-gh-female", "label": "Ama · Ghanaian English", "region": "ghana", "note": "Ghanaian English accent paired with Ghana L1 national models (Twi, Ga, Ewe, Fante, Hausa Zongo) and nearest West African English for Senegal / Côte d'Ivoire French nationals until dedicated en-SN / en-CI accents ship. Never substitutes for L1 French." }, "mt_lang_key": "ak-akuapem", "language_pack_version": "akuapem-pack-2026.10-b", "corridor_id": "en-ak-akuapem", "primary_use": "Education, literary, broadcast orthography", "domains": [ "greetings", "public_services", "education", "health", "civic", "customer_support" ], "dataset_manifest": "apps/api/eval/baobab-twi/dataset-manifest.akuapem.json", "trainingEligible": false, "not_interchangeable_with": [ "ak-gh-asante", "ak-gh-asante-twi", "ak-gh-fante" ], "mt": { "status": "phrase_table_only", "pairs": [ "en↔ak-akuapem" ], "phase_b_expanded": true, "note": "Separate Akuapem Phase B phrase table. Fail-closed when uncovered." }, "asr": { "status": "neural_offline", "checkpoint": "tiffany101/whisper-twi-v2", "license": "Apache-2.0", "env_gate": "Akuapem / Asante speech", "variety_exclusive_finetune": false }, "tts": { "status": "neural_offline", "checkpoint": "onnx-community/mms-tts-aka-ONNX", "license": "CC-BY-NC-4.0", "env_gate": "Akuapem / Asante speech", "variety_exclusive_finetune": false }, "s2s_corridor": { "status": "corridor_pass", "note": "Corridor scripts PASS. Upstream speech is Akan/Twi-general; variety via orthography + rescoring." }, "speech_finetune_recipe": "docs/baobab/SPEECH_FINETUNE_RECIPE.md" } ], "national_tiers": [ { "id": "public_demo", "name": "Public demo", "who": "Citizens, press, students (unauthenticated demos)", "auth": "None — soft abuse controls on demo speech", "maps_to_plan": null, "endpoints": [ "GET /v1/models/baobab-twi", "GET /v1/baobab/twi/national", "POST /v1/demo/speech" ], "limits": { "translate_chars_daily_hint": "Authenticated translate required for production MT", "demo_speech": "400 requests / 10 minutes / IP (demo controller)", "rate_limit_note": "Demo speech returns rate_limited when exceeded" }, "controls": [ "honest en-GH remap when speech URL offline (paired Ghanaian English accent)", "variety headers on Akan demos" ], "residency_preference": null, "audit": false, "commercial_nc_clean_tts_required": false }, { "id": "education", "name": "Education / free", "who": "Students, KNUST labs, research orgs on Free/Pro plans", "auth": "Org API key (TranslateAuthGuard) — Free or Pro plan", "maps_to_plan": "free|pro", "endpoints": [ "POST /v1/translate", "POST /v1/tts/synthesize", "POST /v1/audio/transcriptions (when ASR keyed)", "GET /v1/models/baobab-twi" ], "limits": { "translate_chars_daily_hint": "Free: BILLING_FREE_TRANSLATE_CHARS_QUOTA (default 50k); Pro: BILLING_PRO_TRANSLATE_CHARS_QUOTA", "demo_speech": null, "rate_limit_note": "RATE_LIMIT_FREE_PER_KEY / RATE_LIMIT_PRO_PER_KEY via existing RateLimitGuard" }, "controls": [ "UsageService metering", "BillingService.assertWithinQuota" ], "residency_preference": "GH", "audit": true, "commercial_nc_clean_tts_required": false }, { "id": "ministry", "name": "Ministry production", "who": "Ghana government services", "auth": "Ministry-keyed org API key — Business plan mapping", "maps_to_plan": "business", "endpoints": [ "POST /v1/translate", "POST /v1/tts/synthesize", "MeetingBridge Ghana corridor", "GET /v1/residency", "GET /v1/metrics/translate" ], "limits": { "translate_chars_daily_hint": "Business translate quota (BILLING_BUSINESS_TRANSLATE_CHARS_QUOTA)", "demo_speech": null, "rate_limit_note": "RATE_LIMIT_BUSINESS_PER_KEY / PER_ORG" }, "controls": [ "AuditService on translate.completed", "Org retention / vendor-training settings", "Residency preference GH (affinity, not hard geo-fence)" ], "residency_preference": "GH", "audit": true, "commercial_nc_clean_tts_required": false }, { "id": "enterprise", "name": "Enterprise", "who": "Banks, telcos, NGOs", "auth": "Paid Enterprise keys", "maps_to_plan": "enterprise", "endpoints": [ "POST /v1/translate (+ TM / quality)", "Speech + MeetingBridge", "Fine-tunes / marketplace where plan allows" ], "limits": { "translate_chars_daily_hint": "Enterprise translate quota", "demo_speech": null, "rate_limit_note": "RATE_LIMIT_ENTERPRISE_PER_KEY / PER_ORG" }, "controls": [ "SLA targets (documented; contractual SLA separate)", "Commercial TTS path must be NC-clean for redistribution of MMS weights", "Audit + retention" ], "residency_preference": "AF", "audit": true, "commercial_nc_clean_tts_required": true } ], "research": { "id": "baobab-twi-generative-lm", "status": "research_planned", "foundation_llm_weights": false, "generative_inference_live": false, "ships_trained_baobab_foundation": false, "separate_variety_checkpoints_required": true, "proposed_checkpoint_ids": { "asante": "baobab-twi-asante-lm-*", "akuapem": "baobab-twi-akuapem-lm-*", "never_one_blob": true }, "prerequisites": [ "Phases A–C corridor + national API surfaces remain the product wedge", "Mix / Fidelity / Live Twi–English evals and rights clear", "Consented parallel + speech data per variety with held-outs" ], "acceptance_gates": [ { "id": "held_out_speakers", "required": true, "met": false, "description": "Held-out evaluation speakers must never appear in training exports; speaker lists remain empty until consented collection." }, { "id": "community_consent_asante_and_akuapem", "required": true, "met": false, "description": "trainingEligible stays false until community Asante and Akuapem speakers re-confirm for training." }, { "id": "separate_variety_adapters", "required": true, "met": false, "description": "Any future LM/adapters must ship as baobab-twi-asante-* and baobab-twi-akuapem-* — never one blob marketed as both." }, { "id": "beat_phrase_mt_baselines", "required": true, "met": false, "description": "Generative claims require held-out gains vs corridor phrase-MT baselines on declared Twi-native tasks (Mix/Fidelity/Live gates)." }, { "id": "commercial_rights_clear", "required": true, "met": false, "description": "Base model + data licenses must clear commercial ministry/enterprise redistribution before promotion." } ], "task_harness": { "goldens": "apps/api/eval/baobab-twi/goldens.phase-d-tasks.json", "runner": "apps/api/src/baobab/baobab-twi.research.ts#evaluateBaobabTwiNativeTasks", "generative_default": "unsupported" }, "training_recipe": "docs/baobab/GENERATIVE_LM_RECIPE.md", "note": "Research slot + harness + training recipe only. Do not brand phrase/NLLB MT or speech corridors as a full national LLM. Generative inference unsupported until gates are met and Lugemi-owned weights exist." }, "training_eligible_unlock": { "trainingEligible": false, "status": "locked", "unlock_doc": "docs/baobab/TRAINING_ELIGIBLE_UNLOCK.md", "gates": [ { "id": "community_consent_asante", "required": true, "met": false, "evidence_required": "Signed Asante contributor agreements reconfirming training use", "description": "Asante community speakers must reconfirm training export consent." }, { "id": "community_consent_akuapem", "required": true, "met": false, "evidence_required": "Signed Akuapem contributor agreements reconfirming training use", "description": "Akuapem community speakers must reconfirm training export consent." }, { "id": "held_out_speaker_lists", "required": true, "met": false, "evidence_required": "Published held-out speaker IDs never present in train splits", "description": "Held-out evaluation speakers must never appear in training exports." }, { "id": "dual_variety_native_review", "required": true, "met": false, "evidence_required": "Paid Asante + Akuapem native review records with trainingEligible fields", "description": "Native review must cover both varieties separately before any train export." }, { "id": "rights_clear_for_export", "required": true, "met": false, "evidence_required": "Legal memo clearing commercial vs research split for export corpus", "description": "IP / commercial rights must clear before trainingEligible flips." } ], "note": "trainingEligible remains false until all gates are met with durable evidence. Do not invent consent." }, "license_warnings": [ "MMS TTS (mms-tts-aka) is CC-BY-NC-4.0 — unrestricted commercial redistribution of those weights is blocked.", "Whisper-twi-v2 is Apache-2.0; attribute and pin versions.", "NLLB-200 distilled (baobab-twi-mt) is CC-BY-NC — commercial_license_cleared false; fail-closed phrase MT remains available.", "Phrase/lexical Baobab MT covers reviewed domains; neural NMT when live is NC-restricted." ], "capabilities": { "phrase_mt": "phrase_table_only", "phrase_mt_phase_b_domains": true, "national_api_tiers": true, "generative_lm_research_slot": true, "generative_inference_live": false, "neural_nmt": false, "neural_asr": false, "neural_tts": false, "s2s_corridor": true, "foundation_llm_weights": false }, "honesty": { "phrase_table_only": true, "phrase_coverage_expanded_phase_b": true, "national_api_tiers_phase_c": true, "phase_d_research_shipped": true, "post_d_national_readiness": true, "deferred_slice_shipped": true, "neural_speech_live": false, "neural_nmt": false, "generative_inference_live": false, "foundation_llm_weights": false, "ships_trained_baobab_foundation": false, "asante_akuapem_interchangeable": false, "variety_exclusive_speech_finetunes": false, "trainingEligible": false, "training_eligible_unlock": { "trainingEligible": false, "status": "locked", "unlock_doc": "docs/baobab/TRAINING_ELIGIBLE_UNLOCK.md", "gates": [ { "id": "community_consent_asante", "required": true, "met": false, "evidence_required": "Signed Asante contributor agreements reconfirming training use", "description": "Asante community speakers must reconfirm training export consent." }, { "id": "community_consent_akuapem", "required": true, "met": false, "evidence_required": "Signed Akuapem contributor agreements reconfirming training use", "description": "Akuapem community speakers must reconfirm training export consent." }, { "id": "held_out_speaker_lists", "required": true, "met": false, "evidence_required": "Published held-out speaker IDs never present in train splits", "description": "Held-out evaluation speakers must never appear in training exports." }, { "id": "dual_variety_native_review", "required": true, "met": false, "evidence_required": "Paid Asante + Akuapem native review records with trainingEligible fields", "description": "Native review must cover both varieties separately before any train export." }, { "id": "rights_clear_for_export", "required": true, "met": false, "evidence_required": "Legal memo clearing commercial vs research split for export corpus", "description": "IP / commercial rights must clear before trainingEligible flips." } ], "note": "trainingEligible remains false until all gates are met with durable evidence. Do not invent consent." }, "bare_ak_defaults_to": "ak-gh-asante", "bare_ak_warning": "Bare `ak` / `tw` / `twi` resolves to Asante (`ak-gh-asante`). Pass `ak-gh-akuapem` or `ak-akuapem` for Akuapem. Varieties are never interchangeable. Shared Akan checkpoints + orthography — not exclusive finetunes.", "nmt": { "neural_nmt": false, "disclosed_base_named": "nllb-200-distilled-600M", "disclosed_base_weights_in_repo": false, "commercial_license_cleared": false, "nllb_license": "CC-BY-NC", "adapter_status": "disabled_until_checkpoint", "checkpoint_shipped": false, "remote_mt_configured": false, "remote_mt_env": null, "baobab_twi_nmt_url_configured": false, "baobab_twi_nmt_env": null, "baobab_twi_nmt_live": false, "separate_variety_adapters": false, "note": "Baobab Twi NMT remote not live. Phrase/lexical packs remain the fail-closed default. Optional BAOBAB_TWI_NMT_URL / LUGEMI_MT_URL when set. NLLB base is CC-BY-NC." }, "residency": { "serving_today": "jnb", "serving_today_label": "Africa-primary Fly region Johannesburg (jnb)", "affinity_target": "af-west-1", "affinity_city": "Accra", "affinity_country": "GH", "accra_gpu_island": false, "accra_gpu_island_status": "deferred", "hard_geo_fence": false, "preference_model": "affinity_not_hard_fence", "ministry_affinity_pin": "af-west-1", "affinity_enforcement": "soft_preference_recorded", "accra_island_runbook": "docs/baobab/ACCRA_RESIDENCY.md", "note": "Inference prefers matching person/org residency to nearby model hosting when ready — affinity, not a hard geo-fence. Accra (af-west-1) is the Ghana affinity target; live serving for verbalab + lugemi-asante + baobab-twi-mt is jnb today. No Accra GPU island is deployed. Ministry requests record X-Lugemi-Residency-Affinity soft pin." }, "licenses": { "mms_tts_aka": "CC-BY-NC-4.0", "whisper_twi_v2": "Apache-2.0", "nllb_200_distilled": "CC-BY-NC", "mms_commercial_redistribution": "restricted_nc", "nllb_commercial_redistribution": "restricted_nc", "note": "MMS TTS and NLLB distilled are CC-BY-NC — commercial redistribution restricted. Whisper-twi-v2 is Apache-2.0. neural_nmt true only when NMT health probe succeeds." }, "deferred": [ "Commercially cleared NMT + variety-exclusive adapters (NLLB NC live path ≠ commercial clear)", "Accra GPU island / hard Ghana geo-fence (affinity af-west-1; serving jnb)", "Contractual ministry SLA signature (operational targets shipped)", "Generative Twi LM weights + inference (recipe + gates only)", "Variety-exclusive ASR/TTS finetunes (recipe shipped; shared checkpoints live)", "trainingEligible unlock evidence (checklist shipped; flag locked false)" ] }, "endpoints": { "model_card": "GET /v1/models/baobab-twi", "national": "GET /v1/baobab/twi/national", "research": "GET /v1/baobab/twi/research", "unlock": "GET /v1/baobab/twi/unlock", "slo": "GET /v1/baobab/twi/slo", "translate": "POST /v1/translate", "demo_speech": "POST /v1/demo/speech", "tts": "POST /v1/tts/synthesize", "meetingbridge_ghana": "MeetingBridge Ghana corridor", "dataset_manifests": "apps/api/eval/baobab-twi/dataset-manifest.*.json", "residency": "GET /v1/residency", "translate_metrics": "GET /v1/metrics/translate" }, "docs": { "national_model": "docs/baobab/TWI_NATIONAL_MODEL.md", "model_card": "docs/baobab/baobab-twi.MODEL_CARD.md", "partnership_open_eval": "docs/baobab/PARTNERSHIP_OPEN_EVAL.md", "ministry_sla": "docs/baobab/MINISTRY_SLA.md", "training_eligible_unlock": "docs/baobab/TRAINING_ELIGIBLE_UNLOCK.md", "speech_finetune_recipe": "docs/baobab/SPEECH_FINETUNE_RECIPE.md", "generative_lm_recipe": "docs/baobab/GENERATIVE_LM_RECIPE.md", "accra_residency": "docs/baobab/ACCRA_RESIDENCY.md", "asante_corridor": "en-ak-asante", "akuapem_corridor": "en-ak-akuapem", "language_kit": "docs/models/05_LANGUAGE_KIT.md", "residency": "docs/residency.md" }, "as_of": "2026-10-23T10:16:02.781Z" }