diff --git a/models.yaml b/models.yaml index 1f45a2a..542c8ed 100644 --- a/models.yaml +++ b/models.yaml @@ -74,3 +74,22 @@ models: - {name: der_beam4, value: 17.46, source: rababa/docs/RESULTS.md#hebrew-diacritization} parity: {samples: 600, cer_delta: 0.0} license: BSD-3-Clause + tha-g2p-base-1.0: + task: g2p + scripts: [Thai, IPA] + precision: fp32 + filename: tha-g2p-base-1.0-fp32.zip + parts: + - url: https://github.com/interscript/ml-models/releases/download/tha-g2p-base-1.0/tha-g2p-base-1.0-fp32.zip.part-00 + sha256: c4525414e5dec91a54d055ca9f1acd51c198f81fbfc55977aa82c1fb038d58d7 + size: 1500000000 + - url: https://github.com/interscript/ml-models/releases/download/tha-g2p-base-1.0/tha-g2p-base-1.0-fp32.zip.part-01 + sha256: f5d11fbd75f92e8b5471add867418e2dd4f49a5e258b9ded2f3b5ffa630abe24 + size: 1281174343 + sha256: f341a5868867a9847d3f897d1fcc4d1d63b9a59b8913871bcf4ecab48f4fa895 + size: 2781174343 + metrics: + - {name: per_teacher, value: 4.43, source: interscript/ml-models docs/RESULTS.md#tha-g2p-base-1.0} + - {name: per_student, value: 9.19, source: interscript/ml-models docs/RESULTS.md#tha-g2p-base-1.0} + parity: {samples: 1219, cer_delta: 0.0} + license: BSD-3-Clause diff --git a/models/tha-g2p-base/tha-g2p-base-1.0.metadata.yaml b/models/tha-g2p-base/tha-g2p-base-1.0.metadata.yaml index fb631e5..673c470 100644 --- a/models/tha-g2p-base/tha-g2p-base-1.0.metadata.yaml +++ b/models/tha-g2p-base/tha-g2p-base-1.0.metadata.yaml @@ -8,25 +8,26 @@ opset: 14 decoder: kv precision: fp32 license: BSD-3-Clause -trained_from: >- - sequence-level KD from the B-K/umt5-thai-g2p-v2-0.5k teacher (4.43% - PER on this harness; secryst's saved umt5 artifacts are unusable — - transformers 5.15 dropped the untied lm_head — and the volume's - epitran corpus is tone-less, so the published 2.32% tier is - unrecoverable until secryst regenerates it); 48,757 beam-4 - teacher-generated labels; ByT5-base init google/byt5-base; checkpoint - secryst-checkpoints:/secryst_thai_g2p_distill_small/run-004/best +trained_from: sequence-level KD from the B-K/umt5-thai-g2p-v2-0.5k teacher (4.43% + PER on this harness; secryst's saved umt5 artifacts are unusable — transformers + 5.15 dropped the untied lm_head — and the volume's epitran corpus is tone-less, + so the published 2.32% tier is unrecoverable until secryst regenerates it); 48,757 + beam-4 teacher-generated labels; ByT5-base init google/byt5-base; checkpoint secryst-checkpoints:/secryst_thai_g2p_distill_small/run-004/best metrics: - - name: per_teacher - value: 4.43 - protocol: >- - beam-4, corpus-level PER (total_ed/total_gold over chars of - joined-piece decode); 1,219 Kaikki Thai test sentences; - B-K/umt5-thai-g2p-v2-0.5k teacher - source: interscript/ml-models docs/RESULTS.md#tha-g2p-base-1.0 - - name: per_student - value: 9.19 - protocol: >- - beam-4, corpus-level PER, same harness as the teacher; gate - +4.76pp <= +5pp (docs/DISTILL-SOURCE-PROMPT.md); exact match 90.81% - source: interscript/ml-models docs/RESULTS.md#tha-g2p-base-1.0 +- name: per_teacher + value: 4.43 + protocol: beam-4, corpus-level PER (total_ed/total_gold over chars of joined-piece + decode); 1,219 Kaikki Thai test sentences; B-K/umt5-thai-g2p-v2-0.5k teacher + source: interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0 +- name: per_student + value: 9.19 + protocol: beam-4, corpus-level PER, same harness as the teacher; gate +4.76pp <= + +5pp (docs/DISTILL-SOURCE-PROMPT.md); exact match 90.81% + source: interscript/interscript-ml docs/RESULTS.md#tha-g2p-base-1.0 +parity: + samples: 1219 + cer_delta: 0.0 +sha256: + decoder-kv.onnx: 357d5c50d7d6832fe7da9f76efb2e2dfdb2707e3abbb93be18a266f4b181b7bc + decoder.onnx: f102db0e8957629f615f78669da6f9959015be07e1c2048185f24100492e98b2 + encoder.onnx: dcaa2fa2e87bc6892babfed859fecdf3f50c4326cf443b04dc8acc939fd523fe