Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion package.json
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,8 @@
"format:check": "prettier --check .",
"test:e2e": "playwright test",
"test:e2e:ui": "playwright test --ui",
"generate:catalogue": "tsx scripts/generate-catalogue.mjs"
"generate:catalogue": "tsx scripts/generate-catalogue.mjs",
"generate:models": "tsx scripts/generate-models.mjs"
},
"dependencies": {
"@asciidoctor/core": "^4.0.6",
Expand Down
72 changes: 72 additions & 0 deletions scripts/generate-models.mjs
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
/**
* Regenerate `src/data/models-catalogue.json` from the model registry
* (interscript-models/models.yaml). Run: `npm run generate:models`.
*/

import { readFileSync, writeFileSync } from "node:fs"
import { join, resolve, dirname } from "node:path"
import { fileURLToPath } from "node:url"
import yaml from "js-yaml"

const __dirname = dirname(fileURLToPath(import.meta.url))
const ROOT = resolve(__dirname, "..")
const REGISTRY = resolve(ROOT, "..", "interscript-models", "models.yaml")
const OUT_PATH = join(ROOT, "src", "data", "models-catalogue.json")

const METRIC_ORDER = [
"der_total_greedy", "der_morph_greedy", "der_teacher_greedy",
"der_teacher_fullset", "wer_wikinews2024_multiref", "wer_wikinews_multiref",
"cer", "per", "em",
]

function humanSize(bytes) {
if (!bytes) return ""
const gib = bytes / 2 ** 30
if (gib >= 1) return `${gib.toFixed(1)} GiB`
return `${(bytes / 2 ** 20).toFixed(0)} MiB`
}

function releaseTag(entry, id) {
const first = (entry.parts || [])[0]
if (first && first.url) {
const m = first.url.match(/releases\/download\/([^/]+)\//)
if (m) return m[1]
}
const alias = (entry.aliases || [])[0]
return alias || id
}

function main() {
const registry = yaml.load(readFileSync(REGISTRY, "utf8"))
const out = {}
for (const [id, e] of Object.entries(registry.models || {})) {
const metrics = (e.metrics || []).map((m) => ({
name: m.name,
value: m.value,
}))
metrics.sort(
(a, b) =>
(METRIC_ORDER.indexOf(a.name) + 1 || 99) -
(METRIC_ORDER.indexOf(b.name) + 1 || 99),
)
out[id] = {
id,
task: e.task || "",
scripts: e.scripts || [],
precision: e.precision || "",
size: e.size || 0,
sizeHuman: humanSize(e.size),
splitParts: (e.parts || []).length || null,
filename: e.filename || "",
releaseTag: releaseTag(e, id),
releaseUrl: `https://github.com/interscript/interscript-models/releases/tag/${releaseTag(e, id)}`,
metrics,
license: e.license || "",
paritySamples: e.parity ? e.parity.samples : null,
}
}
writeFileSync(OUT_PATH, JSON.stringify(out, null, 2) + "\n", "utf8")
console.log(`Generated models catalogue: ${Object.keys(out).length} models → ${OUT_PATH}`)
}

main()
Loading
Loading