Files
sing_detect/detect.ts
youfufan 33c275a114 v6: Tauri (Rust + TS) rewrite, Python as ML sidecar
Cross-platform Stream Studio rewrite. UI/ffmpeg/exports move to Rust+TypeScript; Python shrinks to a thin sidecar that runs inaSpeechSegmenter and emits line-delimited JSON. Detection slice extracted from stream-studio.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-01-06 10:00:00 +00:00

130 lines
5.6 KiB
TypeScript

// Detect view — find singing segments in one video, export editor markers.
import { h, clear, basename, fmtDur } from "../dom";
import { makeProgress, toast, renderSongs } from "../ui";
import {
pickVideo, detectSongs, cancel, exportSegments, onDetectProgress, reveal,
type Segment,
} from "../api";
export interface View { el: HTMLElement; onDrop: (paths: string[]) => void; setVideo: (p: string) => void; }
const FPS = ["29.97", "25", "23.976", "30", "60"];
function numField(label: string, value: number, step = "1"): [HTMLElement, HTMLInputElement] {
const input = h("input", { class: "input", type: "number", value: String(value), step, min: "0" }) as HTMLInputElement;
return [h("div", { class: "field" }, h("label", {}, label), input), input];
}
export function buildDetect(): View {
let running = false;
let segments: Segment[] = [];
let videoPath = "";
const videoInput = h("input", { class: "input grow", placeholder: "Select a video…", readonly: true }) as HTMLInputElement;
const [gapF, gapI] = numField("Merge gap (s)", 10);
const [minF, minI] = numField("Min duration (s)", 20);
const [padF, padI] = numField("Padding (s)", 2);
const fpsSel = h("select", { class: "input" }, ...FPS.map((f) => h("option", { value: f }, f))) as HTMLSelectElement;
const detectBtn = h("button", { class: "btn primary lg", disabled: true }, "🎤 Detect Songs") as HTMLButtonElement;
const stopBtn = h("button", { class: "btn danger", disabled: true }, "■ Stop") as HTMLButtonElement;
const exportBtn = h("button", { class: "btn", disabled: true }, "⬇ Export EDL / CSV") as HTMLButtonElement;
const revealBtn = h("button", { class: "btn ghost", style: "display:none" }, "Show in folder") as HTMLButtonElement;
const progress = makeProgress();
const statsEl = h("div", { class: "pills" });
const songsEl = h("div", { class: "songs" });
let lastExportDir = "";
function setVideo(p: string) {
videoPath = p;
videoInput.value = basename(p);
videoInput.title = p;
detectBtn.disabled = running || !p;
}
async function detect() {
if (!videoPath) return;
running = true;
detectBtn.disabled = true;
stopBtn.disabled = false;
exportBtn.disabled = true;
revealBtn.style.display = "none";
clear(songsEl); clear(statsEl);
progress.reset();
progress.indeterminate(true, "Starting detection…");
const un = await onDetectProgress((msg) => {
progress.indeterminate(true, msg);
progress.appendLog(msg);
});
try {
const res = await detectSongs(videoPath, +gapI.value, +minI.value, +padI.value);
segments = res.segments;
progress.indeterminate(false);
progress.set(1, `Found ${segments.length} singing segment(s).`);
renderSongs(songsEl, segments);
const totalSing = segments.reduce((a, s) => a + s.duration, 0);
statsEl.replaceChildren(
h("span", { class: "pill" }, `${segments.length} songs`),
h("span", { class: "pill" }, `singing ${fmtDur(totalSing)}`),
...Object.entries(res.stats || {}).map(([k, v]) =>
h("span", { class: "pill" }, `${k} ${fmtDur(v as number)}`)),
);
exportBtn.disabled = segments.length === 0;
if (!segments.length) toast("No singing detected — try a larger gap or smaller min duration.", "");
} catch (e) {
const msg = String(e);
progress.indeterminate(false);
if (msg.includes("__cancelled__")) progress.set(0, "Stopped by user.");
else { progress.set(0, "Detection failed."); toast(msg, "err"); }
} finally {
un();
running = false;
stopBtn.disabled = true;
detectBtn.disabled = !videoPath;
}
}
exportBtn.addEventListener("click", async () => {
if (!segments.length) return;
try {
const res = await exportSegments(segments, videoPath, null, +fpsSel.value);
lastExportDir = res.files[0] ?? "";
toast(`Exported ${res.files.length} files`, "ok");
if (lastExportDir) revealBtn.style.display = "";
} catch (e) { toast(String(e), "err"); }
});
revealBtn.addEventListener("click", () => lastExportDir && reveal(lastExportDir));
detectBtn.addEventListener("click", detect);
stopBtn.addEventListener("click", () => cancel());
const el = h("div", { class: "view" },
h("div", { class: "card" },
h("h2", {}, h("span", { class: "step" }, "1"), "Source Video"),
h("div", { class: "row" }, videoInput,
h("button", { class: "btn", onclick: async () => { const p = await pickVideo(); if (p) setVideo(p); } }, "Browse…")),
h("div", { class: "hint", style: "margin-top:8px" }, "Tip: drop a file here, or use a Concat output."),
),
h("div", { class: "card" },
h("h2", {}, h("span", { class: "step" }, "2"), "Detection Settings"),
h("div", { class: "row wrap" },
h("div", { class: "grow", style: "min-width:130px" }, gapF),
h("div", { class: "grow", style: "min-width:130px" }, minF),
h("div", { class: "grow", style: "min-width:130px" }, padF),
h("div", { class: "field", style: "min-width:120px" }, h("label", {}, "FPS (export)"), fpsSel)),
h("div", { class: "hint", style: "margin-top:8px" }, "Singing = \"music\". More chatting between songs → raise the gap. Short covers → lower the min duration."),
),
h("div", { class: "card" },
h("h2", {}, h("span", { class: "step" }, "3"), "Run"),
h("div", { class: "row", style: "margin-bottom:14px" }, detectBtn, stopBtn, exportBtn, revealBtn),
progress.root,
h("div", { style: "margin-top:12px" }, statsEl),
h("div", { style: "margin-top:10px" }, songsEl),
),
);
return { el, onDrop: (paths) => { if (paths[0]) setVideo(paths[0]); }, setVideo };
}