From e97d80cb8eefe9e6b49ad1b5c98f396701600d83 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Sun, 31 May 2026 14:52:16 -0700 Subject: [PATCH] catalog: re-source today's engine defaults from canonical upstreams Replace the invented sample inputs / topk with canonically-sourced values (per CATALOG-CONTRACT source precedence + cite-your-source rule), inline-cited: * dia2-2b/dia2-1b input -> '[S1] Hello Dia2!' (nari-labs/dia2 README example) * zonos input -> 'Zonos uses eSpeak for text to phoneme conversion!' (upstream gradio_interface.py blessed Textbox default) * csm input -> 'Hello from Sesame.' (sesame/csm-1b model card example) * csm topk -> default REMOVED (the card recommends no top-k default; the wrapper's internal default applies when omitted). --- docs/asset-engine/services.yaml | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/docs/asset-engine/services.yaml b/docs/asset-engine/services.yaml index ef5a510..45de993 100644 --- a/docs/asset-engine/services.yaml +++ b/docs/asset-engine/services.yaml @@ -1268,7 +1268,7 @@ services: label: Text ([S1]/[S2] dialogue + nonverbals) required: true max_length: 5000 - default: "[S1] Did it actually work? [S2] (laughs) Worked on the first try." + default: "[S1] Hello Dia2!" # canonical: nari-labs/dia2 README usage example description: > [S1]/[S2] tags mark speaker turns; nonverbals like (laughs), (coughs), (sighs), (clears throat) go inline. @@ -1347,7 +1347,7 @@ services: label: Text ([S1]/[S2] dialogue + nonverbals) required: true max_length: 5000 - default: "[S1] Did it actually work? [S2] (laughs) Worked on the first try." + default: "[S1] Hello Dia2!" # canonical: nari-labs/dia2 README usage example description: > [S1]/[S2] tags mark speaker turns; nonverbals like (laughs), (coughs), (sighs), (clears throat) go inline. @@ -1426,7 +1426,7 @@ services: label: Text required: true max_length: 5000 - default: "Hey, good to finally talk with you. How has your day been?" + default: "Hello from Sesame." # canonical: sesame/csm-1b model card - name: voice type: select label: Voice @@ -1453,8 +1453,7 @@ services: - name: topk type: number required: false - default: 50 - description: Top-k sampling cutoff (1–100). + description: Top-k sampling cutoff (1–100); no canonical default — wrapper's internal default applies if omitted. - name: max_audio_length_ms type: number required: false @@ -1530,7 +1529,7 @@ services: section: text required: true max_length: 500 - default: "This is a quick test of an expressive, multilingual voice." + default: "Zonos uses eSpeak for text to phoneme conversion!" # canonical: upstream gradio_interface.py default description: eSpeak-phonemized. Upstream Gradio caps the box at ~500 chars. - name: language type: select