Spaces:
Sleeping
Sleeping
Commit History
-
Phrasebook eval harness + accent/filler-tolerant matching
ous-sow +1: Claude Opus 5.5- configs/eval/phrasebook_eval.json: 85 held-out inputs (typos, code-switching, filler words, open-ended questions that must reach the LLM), written to differ from the curated aliases. - scripts/eval_phrasebook.py: scores correct / wrong / false_hit / miss per language. - _normalize now folds Latin accents (ça -> ca), drops politeness filler (please, svp, s'il vous plaît) and leading articles (du, une, some). Applied to both sides; Bambara/Pular letters (ɛ ɔ ɓ ŋ) are untouched. Hit rate on the eval set: before aliases bam 43% ful 46% + aliases bam 80% ful 77% + normaliser bam 88% ful 86% wrong=0 and false_hit=0 at every step. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>ea5dc26 -
Phrasebook: +502 English paraphrase and French aliases
ous-sow +1: Claude Opus 5.5Adds sources / source_fr / sources_fr to all 210 curated rows via scripts/add_phrasebook_aliases.py (idempotent, aborts on any alias that would map to two different targets). Bambara and Pular target strings are untouched — verified against HEAD. The two context-dependent Pular "We are working" rows intentionally get no aliases. Bambara: 100 rows -> 340 match keys. Pular: 110 rows -> 363 match keys. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>b8a88ef
-
Ground-zero Stages 1–3: dialect anchors + phrasebook short-circuit + Aya-Expanse
jefffffff9Stage 1 — dialect-pinned LLM client (src/llm/minimal_client.py) Plain-text replacement for GemmaClient's JSON/teacher flow. System prompt pins Bambara-Mali and Pular-Fuuta-Jallon explicitly, names forbidden neighbouring languages (Wolof, Hausa, Pulaar-Senegal, Fulfulde-Nigeria, Jula-CI), and injects a 30-pair bilingual gold list as few-shot anchoring from configs/dialect_anchors/{bambara_mali,pular_guinea}.json. Stage 2 — curated phrasebook short-circuit (src/llm/phrasebook.py) 100 Bambara + 110 Pular English-keyed pairs across greetings, family, food, farming, health, shopping, travel, clarity, time, parting. Fuzzy matched (threshold 0.88) before every LLM call; on hit returns the gold translation directly — zero drift risk, zero latency. Stage 3 — default LLM swapped to CohereLabs/aya-expanse-32b 23-language multilingual base with stronger West African coverage than Qwen 2.5-7B. Overridable via LLM_MODEL_ID. Space wiring - README frontmatter app_file: app.p…d0e28fa
-
Initial commit: Sahel-Agri Voice AI
jefffffff976db545