diff --git a/docs/utterance-embedding.md b/docs/utterance-embedding.md index 15d86ce..181de10 100644 --- a/docs/utterance-embedding.md +++ b/docs/utterance-embedding.md @@ -84,7 +84,7 @@ meaning packet while `panphon_sequence` carries the sound-shape evidence. The first emitted training artifact is `examples/speech-training/tiny-panphon-v0.1/batch.json`. It contains six pure IPA seed packets (`a`, `pa`, `ta`, `ka`, `sa`, and `ma`) with zeroed semantic -text embeddings, inline PanPhon-style feature frames, deterministic +text embeddings, inline PanPhon 22-feature frames, deterministic prosody/emphasis hints, and the Epiphany-compatible neutral 64-slot character state vector. The AquaSynth-owned learned fields are present but marked pending, so training can begin from a real Weksa artifact without pretending @@ -151,9 +151,9 @@ The v0.1 vector names are review labels, not the true learned latent space. They stabilize Weksa output and help humans inspect what the training packet is trying to preserve. -`panphon_sequence` is deterministic speech-surface evidence. Its first v0.1 -implementation should use PanPhon-style ternary articulatory features as the -per-phone spine, then add stress, length, tone, boundary, and timing markers. +`panphon_sequence` is deterministic speech-surface evidence. Its v0.1 +implementation uses PanPhon's 22 ternary articulatory features as the per-phone +spine, then adds stress, length, tone, boundary, and timing markers. It is not a semantic embedding. AquaSynth trains `aquasynth.panphon_sequence_encoder.v0.1` to compress that variable-length sequence into the 256-float `phonetic_realization_embedding`. diff --git a/examples/speech-training/tiny-panphon-v0.1/README.md b/examples/speech-training/tiny-panphon-v0.1/README.md index 5f1c772..e1a2717 100644 --- a/examples/speech-training/tiny-panphon-v0.1/README.md +++ b/examples/speech-training/tiny-panphon-v0.1/README.md @@ -9,7 +9,7 @@ It is intentionally small: six pure IPA packets for `a`, `pa`, `ta`, `ka`, - a 1024-float semantic text embedding reference, zeroed because these are pure IPA fixtures; -- an inline variable-length PanPhon-style feature sequence; +- an inline variable-length PanPhon 22-feature sequence; - 32 Weksa-owned prosody/emphasis hints; - a 64-float Epiphany-compatible neutral character-state vector reference; - pending AquaSynth-owned 256-float phonetic realization and 64-float @@ -25,6 +25,7 @@ Run it from the Weksa repo root: ``` `batch.json` is the training entrypoint for AquaSynth. The individual packet -files are stable seed fixtures; the PanPhon feature values are hand-authored -for this six-phone crawl stage and should be regenerated from the canonical -PanPhon library before Weksa expands coverage. +files are stable seed fixtures. The schema uses PanPhon's 22-feature basis from +the start; the feature values in this six-phone crawl stage are hand-authored +and should be regenerated from the canonical PanPhon library before Weksa +expands coverage. diff --git a/examples/speech-training/tiny-panphon-v0.1/alveolar-ta.json b/examples/speech-training/tiny-panphon-v0.1/alveolar-ta.json index 56223ab..8ec624a 100644 --- a/examples/speech-training/tiny-panphon-v0.1/alveolar-ta.json +++ b/examples/speech-training/tiny-panphon-v0.1/alveolar-ta.json @@ -15,7 +15,7 @@ "values_ref": "vectors/zero-semantic-1024.json" }, "panphon_sequence": { - "model_id": "panphon-style.v0.1.seed", + "model_id": "panphon.v0.1.seed", "source": "hand-authored seed phones for AquaSynth crawl-stage parity tests", "ipa": "ta", "feature_order": [ @@ -238,7 +238,7 @@ ], "notes": [ "This fixture is a crawl-stage training seed, not a full English lowering artifact.", - "PanPhon-style features are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", + "The schema uses PanPhon's 22-feature basis; these seed values are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", "AquaSynth owns the learned 256-float phonetic realization embedding and 64-float utterance embedding." ], "uncertainties": [ diff --git a/examples/speech-training/tiny-panphon-v0.1/bilabial-pa.json b/examples/speech-training/tiny-panphon-v0.1/bilabial-pa.json index 3927a0f..8a0a1c0 100644 --- a/examples/speech-training/tiny-panphon-v0.1/bilabial-pa.json +++ b/examples/speech-training/tiny-panphon-v0.1/bilabial-pa.json @@ -15,7 +15,7 @@ "values_ref": "vectors/zero-semantic-1024.json" }, "panphon_sequence": { - "model_id": "panphon-style.v0.1.seed", + "model_id": "panphon.v0.1.seed", "source": "hand-authored seed phones for AquaSynth crawl-stage parity tests", "ipa": "pa", "feature_order": [ @@ -238,7 +238,7 @@ ], "notes": [ "This fixture is a crawl-stage training seed, not a full English lowering artifact.", - "PanPhon-style features are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", + "The schema uses PanPhon's 22-feature basis; these seed values are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", "AquaSynth owns the learned 256-float phonetic realization embedding and 64-float utterance embedding." ], "uncertainties": [ diff --git a/examples/speech-training/tiny-panphon-v0.1/nasal-ma.json b/examples/speech-training/tiny-panphon-v0.1/nasal-ma.json index f17908c..3a87223 100644 --- a/examples/speech-training/tiny-panphon-v0.1/nasal-ma.json +++ b/examples/speech-training/tiny-panphon-v0.1/nasal-ma.json @@ -15,7 +15,7 @@ "values_ref": "vectors/zero-semantic-1024.json" }, "panphon_sequence": { - "model_id": "panphon-style.v0.1.seed", + "model_id": "panphon.v0.1.seed", "source": "hand-authored seed phones for AquaSynth crawl-stage parity tests", "ipa": "ma", "feature_order": [ @@ -238,7 +238,7 @@ ], "notes": [ "This fixture is a crawl-stage training seed, not a full English lowering artifact.", - "PanPhon-style features are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", + "The schema uses PanPhon's 22-feature basis; these seed values are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", "AquaSynth owns the learned 256-float phonetic realization embedding and 64-float utterance embedding." ], "uncertainties": [ diff --git a/examples/speech-training/tiny-panphon-v0.1/open-vowel-a.json b/examples/speech-training/tiny-panphon-v0.1/open-vowel-a.json index 51b8a13..cba038e 100644 --- a/examples/speech-training/tiny-panphon-v0.1/open-vowel-a.json +++ b/examples/speech-training/tiny-panphon-v0.1/open-vowel-a.json @@ -15,7 +15,7 @@ "values_ref": "vectors/zero-semantic-1024.json" }, "panphon_sequence": { - "model_id": "panphon-style.v0.1.seed", + "model_id": "panphon.v0.1.seed", "source": "hand-authored seed phones for AquaSynth crawl-stage parity tests", "ipa": "a", "feature_order": [ @@ -203,7 +203,7 @@ ], "notes": [ "This fixture is a crawl-stage training seed, not a full English lowering artifact.", - "PanPhon-style features are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", + "The schema uses PanPhon's 22-feature basis; these seed values are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", "AquaSynth owns the learned 256-float phonetic realization embedding and 64-float utterance embedding." ], "uncertainties": [ diff --git a/examples/speech-training/tiny-panphon-v0.1/sibilant-sa.json b/examples/speech-training/tiny-panphon-v0.1/sibilant-sa.json index 20cfe2d..d50974b 100644 --- a/examples/speech-training/tiny-panphon-v0.1/sibilant-sa.json +++ b/examples/speech-training/tiny-panphon-v0.1/sibilant-sa.json @@ -15,7 +15,7 @@ "values_ref": "vectors/zero-semantic-1024.json" }, "panphon_sequence": { - "model_id": "panphon-style.v0.1.seed", + "model_id": "panphon.v0.1.seed", "source": "hand-authored seed phones for AquaSynth crawl-stage parity tests", "ipa": "sa", "feature_order": [ @@ -238,7 +238,7 @@ ], "notes": [ "This fixture is a crawl-stage training seed, not a full English lowering artifact.", - "PanPhon-style features are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", + "The schema uses PanPhon's 22-feature basis; these seed values are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", "AquaSynth owns the learned 256-float phonetic realization embedding and 64-float utterance embedding." ], "uncertainties": [ diff --git a/examples/speech-training/tiny-panphon-v0.1/velar-ka.json b/examples/speech-training/tiny-panphon-v0.1/velar-ka.json index 2446a6c..2ebdc3b 100644 --- a/examples/speech-training/tiny-panphon-v0.1/velar-ka.json +++ b/examples/speech-training/tiny-panphon-v0.1/velar-ka.json @@ -15,7 +15,7 @@ "values_ref": "vectors/zero-semantic-1024.json" }, "panphon_sequence": { - "model_id": "panphon-style.v0.1.seed", + "model_id": "panphon.v0.1.seed", "source": "hand-authored seed phones for AquaSynth crawl-stage parity tests", "ipa": "ka", "feature_order": [ @@ -238,7 +238,7 @@ ], "notes": [ "This fixture is a crawl-stage training seed, not a full English lowering artifact.", - "PanPhon-style features are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", + "The schema uses PanPhon's 22-feature basis; these seed values are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", "AquaSynth owns the learned 256-float phonetic realization embedding and 64-float utterance embedding." ], "uncertainties": [ diff --git a/schemas/utterance-embedding-handoff.md b/schemas/utterance-embedding-handoff.md index b6d669f..ae25a64 100644 --- a/schemas/utterance-embedding-handoff.md +++ b/schemas/utterance-embedding-handoff.md @@ -60,7 +60,7 @@ phonetic fixtures may zero `inputs.speech_text_embedding` or point it to a source meaning packet, but they must not smuggle phone strings through the semantic-text channel. -The v0.1 phonetic channel uses PanPhon-style articulatory features as its +The v0.1 phonetic channel uses PanPhon's 22 articulatory features as its per-phone base representation. Weksa supplies that sequence evidence. AquaSynth owns the learned compression from variable-length PanPhon sequence into the 256-float `phonetic_realization_embedding`. @@ -68,5 +68,5 @@ owns the learned compression from variable-length PanPhon sequence into the The first machine-readable seed batch lives at `examples/speech-training/tiny-panphon-v0.1/batch.json`. It is the minimal artifact AquaSynth should consume before broader English or alien pronunciation -coverage: six pure IPA packets with fixed vector widths, inline PanPhon-style -frames, and pending AquaSynth-owned learned outputs. +coverage: six pure IPA packets with fixed vector widths, inline PanPhon +22-feature frames, and pending AquaSynth-owned learned outputs. diff --git a/state/map.yaml b/state/map.yaml index 04039c8..97bc51d 100644 --- a/state/map.yaml +++ b/state/map.yaml @@ -232,7 +232,8 @@ landed_baseline: `tools/emit_tiny_panphon_handoffs.py`. - First machine-readable AquaSynth speech-training seed batch at `examples/speech-training/tiny-panphon-v0.1/batch.json`, covering pure IPA - `a`, `pa`, `ta`, `ka`, `sa`, and `ma` with fixed v0.1 vector widths. + `a`, `pa`, `ta`, `ka`, `sa`, and `ma` with fixed v0.1 vector widths and + PanPhon's 22-feature basis. - Weksa-to-AquaSynth utterance embedding handoff v0.1 fixes the training vector contract: 1024-float `bge-m3:latest` speech text embedding, variable-length PanPhon sequence evidence, a 256-float AquaSynth-owned diff --git a/tools/emit_tiny_panphon_handoffs.py b/tools/emit_tiny_panphon_handoffs.py index 271b97a..3df7d4e 100644 --- a/tools/emit_tiny_panphon_handoffs.py +++ b/tools/emit_tiny_panphon_handoffs.py @@ -2,9 +2,9 @@ """Emit tiny v0.1 utterance handoff fixtures for AquaSynth speech training. This is intentionally not a Weksa runtime. It is a deterministic artifact -emitter for the first crawl-stage curriculum: simple IPA syllables with -PanPhon-style feature frames, fixed-width Weksa/Epiphany input vectors, and -pending AquaSynth-owned learned outputs. +emitter for the first crawl-stage curriculum: simple IPA syllables with the +PanPhon 22-feature basis, fixed-width Weksa/Epiphany input vectors, and pending +AquaSynth-owned learned outputs. """ from __future__ import annotations @@ -265,7 +265,7 @@ def packet(packet_id: str, ipa: str, phones: list[str], note: str) -> dict: "values_ref": "vectors/zero-semantic-1024.json", }, "panphon_sequence": { - "model_id": "panphon-style.v0.1.seed", + "model_id": "panphon.v0.1.seed", "source": "hand-authored seed phones for AquaSynth crawl-stage parity tests", "ipa": ipa, "feature_order": FEATURE_ORDER, @@ -328,7 +328,7 @@ def packet(packet_id: str, ipa: str, phones: list[str], note: str) -> dict: ], "notes": [ "This fixture is a crawl-stage training seed, not a full English lowering artifact.", - "PanPhon-style features are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", + "The schema uses PanPhon's 22-feature basis; these seed values are hand-authored for the six seed phones until Weksa wires a canonical PanPhon dependency.", "AquaSynth owns the learned 256-float phonetic realization embedding and 64-float utterance embedding.", ], "uncertainties": [