diff --git a/corpora/khm-latn.yaml b/corpora/khm-latn.yaml index 43379ce..1d982e5 100644 --- a/corpora/khm-latn.yaml +++ b/corpora/khm-latn.yaml @@ -1,16 +1,21 @@ id: khm-latn task: transliteration sources: - # WO88 migration: the secryst-era khm-latn training lineage, recorded - # with honest provenance markers — the original corpus predates the - # pinning contract. Decode evidence + the khmer-dict-spice source - # (Chuon Nath + SBBIC) are documented; the exact training tsv/tsv - # generation script lives in the secryst repo - # (scripts/export_onnx_byt5.py lineage). UNVERIFIED fields are the - # retrain blockers listed in WO68/88. + # WO68 lineage recovery (2026-10-29): the secryst-era khm-latn training + # corpus identified exactly as secryst/data-khmer-translit — 17,911 word + # pairs in two parallel single-column CSVs. Staged to the training bucket + # with sha256; the legacy raw.githubusercontent fetch is retired. + # Upstream repo carries no license file (predecessor project's own); + # the ship gate stays owner-held until the license_review record lands. - kind: repo - id: secryst (~/src/interscript/secryst lineage) - license: UNVERIFIED - provenance: UNVERIFIED — recover the exact training corpus before any retrain + id: secryst/data-khmer-translit + license: UNVERIFIED — predecessor repo, no license file; owner decision pending + provenance: https://github.com/secryst/data-khmer-translit (master at recovery, 2026-10-29) splits: - train: {path: UNVERIFIED, rows: 0, sha256: UNVERIFIED} + train: {path: hf://buckets/Interscript/isx-training/khmer-translit/run-081-recovery/train.jsonl, rows: 16120, sha256: SEE-RUN} + val: {path: hf://buckets/Interscript/isx-training/khmer-translit/run-081-recovery/val.jsonl, rows: 895, sha256: SEE-RUN} + test: {path: hf://buckets/Interscript/isx-training/khmer-translit/run-081-recovery/test.jsonl, rows: 895, sha256: SEE-RUN} +raw: + data_kh.csv: {sha256: 48f9924ac50c941c1fd52a7e5a9152e4478ba6d9679e1732333ed9f76b598a81, path: hf://buckets/Interscript/isx-training/khmer-translit/data_kh.csv, rows: 17911} + data_rom.csv: {sha256: 7dff342f4ed214c05d147e71baa10482d80f4ff6d182ee15a2abbdbafb6bc71b, path: hf://buckets/Interscript/isx-training/khmer-translit/data_rom.csv, rows: 17911} +recovery_run: run-081-khm-latn-recovery (HF job rhtse/6ae32acd41e90535df78a449, seed 42, recipe = legacy run-001)