hyperframes 0.8.57 → 0.8.59

package/dist/skills/media-use/scripts/transcribe.mjs

@@ -0,0 +1,180 @@
+#!/usr/bin/env node
+
+import { execFileSync } from "node:child_process";
+import {
+  existsSync,
+  readFileSync,
+  writeFileSync,
+  copyFileSync,
+  renameSync,
+  mkdtempSync,
+  rmSync,
+} from "node:fs";
+import { homedir, tmpdir } from "node:os";
+import { basename, extname, join, resolve } from "node:path";
+import { parseArgs } from "node:util";
+import { mergeTokensToWords } from "./lib/parakeet-words.mjs";
+import { track } from "./lib/telemetry.mjs";
+import { resolveNpxInvocation } from "./lib/npx-sync.mjs";
+
+// The DEFAULT local transcription path. Prefers NVIDIA Parakeet-TDT via
+// parakeet-mlx, which beats whisper.cpp on the Open ASR Leaderboard (~6.05% vs
+// 7.44% avg WER, and 4.73% vs 5.96% on noisy test-other) and is 5-10x faster
+// with native punctuation. Emits { text, words:[{text,start,end}] } (word
+// timestamps merged from Parakeet's sub-word tokens) for transcript-cut /
+// captions / the audio engine.
+//
+// Parakeet v3 covers English + 25 European languages. For other languages, or
+// when parakeet-mlx is not installed, it falls back to whisper.cpp via
+// `hyperframes transcribe` (99 languages; the CLI resolves/builds whisper.cpp
+// on first use — it is not bundled). `--engine` forces one.
+
+const { values: args } = parseArgs({
+  options: {
+    input: { type: "string", short: "i" },
+    out: { type: "string", short: "o" },
+    engine: { type: "string", default: "auto" }, // auto | parakeet | whisper
+    model: { type: "string", default: "mlx-community/parakeet-tdt-0.6b-v3" },
+    json: { type: "boolean", default: false },
+    help: { type: "boolean", short: "h", default: false },
+  },
+  strict: true,
+});
+
+if (args.help) {
+  console.log(`media-use transcribe: better-than-whisper local ASR (Parakeet), whisper.cpp fallback
+
+Usage:
+  node transcribe.mjs --input audio.wav [--out audio.transcribe.json] [--engine auto|parakeet|whisper]
+
+Parakeet (default) beats whisper.cpp on accuracy + speed for English/European
+languages; whisper.cpp (99 languages) is the fallback. Install Parakeet once:
+  uv venv ~/.venvs/parakeet && VIRTUAL_ENV=~/.venvs/parakeet uv pip install parakeet-mlx`);
+  process.exit(0);
+}
+
+if (!args.input) {
+  console.error("error: --input is required");
+  process.exit(2);
+}
+const inputPath = resolve(args.input);
+if (!existsSync(inputPath)) {
+  console.error(`error: input not found: ${inputPath}`);
+  process.exit(2);
+}
+const outPath = resolve(
+  args.out || `${inputPath.slice(0, -extname(inputPath).length)}.transcribe.json`,
+);
+
+// Locate the parakeet-mlx runner the same way the CLI does: env override, then
+// the documented ~/.venvs/parakeet install, then PATH. Checking the venv (not
+// just PATH) is what keeps a user who followed the install docs verbatim from
+// silently falling through to whisper. Returns the runner path, or null.
+function resolveParakeet() {
+  for (const p of [
+    process.env.HYPERFRAMES_PARAKEET,
+    join(homedir(), ".venvs", "parakeet", "bin", "parakeet-mlx"),
+  ]) {
+    if (p && existsSync(p)) return p;
+  }
+  try {
+    execFileSync("parakeet-mlx", ["--help"], {
+      stdio: ["ignore", "ignore", "ignore"],
+      timeout: 20000,
+    });
+    return "parakeet-mlx";
+  } catch {
+    return null;
+  }
+}
+
+// Write via a sibling temp + atomic rename so a SIGKILL mid-write can't leave a
+// truncated transcript at outPath (downstream reads it as valid JSON).
+function atomicWrite(target, data) {
+  const tmp = `${target}.tmp-${process.pid}`;
+  writeFileSync(tmp, data);
+  renameSync(tmp, target);
+}
+
+function report(engine, wordCount) {
+  if (args.json) console.log(JSON.stringify({ ok: true, out: outPath, engine, words: wordCount }));
+  else
+    console.log(
+      `transcribed ${basename(inputPath)} -> ${outPath}${wordCount != null ? ` (${wordCount} words,` : " ("}${engine})`,
+    );
+}
+
+function runParakeet(runner) {
+  const workDir = mkdtempSync(join(tmpdir(), "media-use-asr-"));
+  try {
+    execFileSync(
+      runner,
+      [inputPath, "--model", args.model, "--output-format", "json", "--output-dir", workDir],
+      { stdio: ["ignore", "pipe", "pipe"], timeout: 1_800_000 },
+    );
+    const jsonPath = join(workDir, `${basename(inputPath, extname(inputPath))}.json`);
+    if (!existsSync(jsonPath)) throw new Error("parakeet produced no JSON");
+    const merged = mergeTokensToWords(JSON.parse(readFileSync(jsonPath, "utf8")));
+    atomicWrite(outPath, JSON.stringify(merged, null, 2));
+    report("parakeet", merged.words.length);
+  } finally {
+    rmSync(workDir, { recursive: true, force: true });
+  }
+}
+
+// whisper.cpp via the hyperframes CLI (fetched/built on first use — see
+// SKILL.md): writes transcript.json into --dir; relocate to --out.
+function runWhisper() {
+  const workDir = mkdtempSync(join(tmpdir(), "media-use-whisper-"));
+  try {
+    // On Windows a bare "npx" is npx.cmd, which execFileSync cannot exec
+    // (spawnSync npx ENOENT) — resolveNpxInvocation reroutes it through
+    // node + npx-cli.js (and throws actionably when it can't), same
+    // mechanism as the audio engine's TTS spawns.
+    const resolved = resolveNpxInvocation(
+      ["hyperframes", "transcribe", inputPath, "--dir", workDir],
+      { stdio: ["ignore", "pipe", "pipe"], timeout: 1_800_000 },
+    );
+    execFileSync(resolved.cmd, resolved.args, resolved.opts);
+    const produced = join(workDir, "transcript.json");
+    if (!existsSync(produced)) throw new Error("whisper produced no transcript.json");
+    const tmp = `${outPath}.tmp-${process.pid}`;
+    copyFileSync(produced, tmp);
+    renameSync(tmp, outPath); // atomic publish
+    let words;
+    try {
+      const t = JSON.parse(readFileSync(outPath, "utf8"));
+      words = Array.isArray(t?.words) ? t.words.length : undefined;
+    } catch {
+      /* leave undefined */
+    }
+    report("whisper", words);
+  } finally {
+    rmSync(workDir, { recursive: true, force: true });
+  }
+}
+
+try {
+  const parakeetBin = resolveParakeet();
+  const engine =
+    args.engine === "parakeet" || args.engine === "whisper"
+      ? args.engine
+      : parakeetBin
+        ? "parakeet"
+        : "whisper";
+  if (engine === "parakeet") {
+    if (!parakeetBin) {
+      throw new Error(
+        "parakeet-mlx not found (checked $HYPERFRAMES_PARAKEET, ~/.venvs/parakeet, and PATH). Install: uv venv ~/.venvs/parakeet && VIRTUAL_ENV=~/.venvs/parakeet uv pip install parakeet-mlx (or use --engine whisper)",
+      );
+    }
+    runParakeet(parakeetBin);
+  } else {
+    runWhisper();
+  }
+  await track("media_use_transcribe", { engine });
+} catch (err) {
+  if (args.json) console.log(JSON.stringify({ ok: false, error: err.message }));
+  else console.error(`error: transcription failed: ${err.message}`);
+  process.exit(1);
+}

package/dist/skills/media-use/scripts/transcript-cut.mjs

@@ -0,0 +1,239 @@
+#!/usr/bin/env node
+
+import { execFileSync } from "node:child_process";
+import { mkdtempSync, mkdirSync, readFileSync, renameSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { dirname, extname, join, resolve } from "node:path";
+import { parseArgs } from "node:util";
+import { compileCutList } from "./lib/cutlist.mjs";
+import { track } from "./lib/telemetry.mjs";
+
+const { values: args } = parseArgs({
+  options: {
+    input: { type: "string" },
+    transcript: { type: "string" },
+    remove: { type: "string" },
+    "remove-words": { type: "string" },
+    "remove-fillers": { type: "string" },
+    "cut-silence": { type: "string" },
+    keep: { type: "string" },
+    copy: { type: "boolean", default: false },
+    plan: { type: "boolean", default: false },
+    out: { type: "string" },
+    json: { type: "boolean", default: false },
+    help: { type: "boolean", short: "h", default: false },
+  },
+  strict: true,
+});
+
+if (args.help) {
+  console.log(`media-use transcript-cut — compile transcript edits into video cuts
+
+Usage:
+  node transcript-cut.mjs --input in.mp4 --transcript transcript.json --remove "12-15" --out out.mp4
+
+Options:
+  --input             Source video/audio file
+  --transcript        JSON word transcript, array or { words: [...] }
+  --remove            Time ranges to remove, seconds: a-b,c-d
+  --remove-words      Word-index ranges to remove: 12-18,40-41
+  --remove-fillers    Comma list of filler words to remove
+  --cut-silence       Remove inter-word gaps longer than this many seconds
+  --keep              Inverse mode: direct kept ranges, mutually exclusive with removal
+  --copy              Use stream copy for faster, keyframe-snapped cuts
+  --plan              Print kept segment JSON and exit without ffmpeg
+  --out               Output file
+  --json              Output JSON status
+  --help, -h          Show this help`);
+  process.exit(0);
+}
+
+try {
+  run();
+  await track("media_use_transcript_cut", {
+    mode: args.plan ? "plan" : "encode",
+    remove_fillers: !!args["remove-fillers"],
+    cut_silence: !!args["cut-silence"],
+    ranges: !!args.remove,
+    keep: !!args.keep,
+  });
+} catch (err) {
+  if (args.json) console.log(JSON.stringify({ ok: false, error: err.message }));
+  else console.error(`error: ${err.message}`);
+  process.exit(1);
+}
+
+function run() {
+  if (!args.transcript) throw new Error("--transcript is required");
+  const transcript = JSON.parse(readFileSync(resolve(args.transcript), "utf8"));
+  const segments = compileCutList(transcript, {
+    remove: args.remove,
+    removeWords: args["remove-words"],
+    removeFillers: args["remove-fillers"],
+    cutSilence: args["cut-silence"],
+    keep: args.keep,
+  });
+
+  if (args.plan) {
+    console.log(JSON.stringify(segments));
+    return;
+  }
+
+  if (!args.input || !args.out)
+    throw new Error("--input and --out are required unless --plan is set");
+  if (segments.length === 0) throw new Error("cut list has no kept segments");
+
+  const inputPath = resolve(args.input);
+  const outPath = resolve(args.out);
+  mkdirSync(dirname(outPath), { recursive: true });
+  const tmpDir = mkdtempSync(join(tmpdir(), "media-use-cut-"));
+  const keptSeconds = sumDurations(segments);
+  const totalSeconds = probeDuration(inputPath);
+
+  try {
+    const parts = segments.map((segment, index) => {
+      const out = join(
+        tmpDir,
+        `segment-${String(index).padStart(4, "0")}${extname(outPath) || ".mp4"}`,
+      );
+      cutSegment(inputPath, segment, out, Boolean(args.copy));
+      return out;
+    });
+    const listPath = join(tmpDir, "list.txt");
+    writeFileSync(
+      listPath,
+      parts.map((part) => `file '${escapeConcatPath(part)}'`).join("\n") + "\n",
+    );
+    // Encode to a sibling temp (same extension so ffmpeg picks the right muxer),
+    // then atomic-rename so a SIGKILL mid-encode can't leave a truncated outPath.
+    const tmpOut = `${outPath}.part${extname(outPath) || ".mp4"}`;
+    execFileSync(
+      "ffmpeg",
+      ["-y", "-f", "concat", "-safe", "0", "-i", listPath, "-c", "copy", tmpOut],
+      {
+        stdio: "ignore",
+      },
+    );
+    renameSync(tmpOut, outPath);
+  } finally {
+    rmSync(tmpDir, { recursive: true, force: true });
+  }
+
+  // Stream copy can only cut on keyframes; on sparse-keyframe footage the snap
+  // can silently swallow the whole cut. Compare, then surface the drift in BOTH
+  // the stderr warning (human) and the --json result (pipelines).
+  let copyDrift = null;
+  if (args.copy) {
+    const outSeconds = probeDuration(outPath);
+    if (Math.abs(outSeconds - keptSeconds) > 1) {
+      copyDrift = { produced_s: round3(outSeconds), expected_s: round3(keptSeconds) };
+      if (!args.json) {
+        console.error(
+          `warning: --copy keyframe snapping produced ${round3(outSeconds)}s instead of ${round3(keptSeconds)}s kept; drop --copy for frame-accurate cuts`,
+        );
+      }
+    }
+  }
+
+  if (args.json) {
+    console.log(
+      JSON.stringify({
+        ok: true,
+        input: inputPath,
+        out: outPath,
+        segments,
+        kept_s: round3(keptSeconds),
+        total_s: round3(totalSeconds),
+        ...(copyDrift && { copy_drift: copyDrift }),
+      }),
+    );
+    return;
+  }
+
+  console.log(
+    `cut ${inputPath} -> ${outPath} (${segments.length} segments, ${fmt(keptSeconds)}s kept of ${fmt(
+      totalSeconds,
+    )}s)`,
+  );
+  console.log(`next: resolve --from ${outPath} --type <type>`);
+}
+
+function cutSegment(inputPath, segment, outPath, copy) {
+  const argv = [
+    "-y",
+    "-nostdin",
+    "-ss",
+    fmt(segment.start),
+    "-i",
+    inputPath,
+    "-to",
+    fmt(segment.end - segment.start),
+  ];
+  if (copy) {
+    argv.push("-c", "copy", "-avoid_negative_ts", "make_zero");
+  } else {
+    argv.push(...encodeArgsFor(extname(outPath).toLowerCase()));
+  }
+  argv.push(outPath);
+  execFileSync("ffmpeg", argv, { stdio: "ignore" });
+}
+
+// Codec set per output container. Audio-only outputs must not get the
+// video-centric aac/x264 set (aac inside .wav breaks timing entirely).
+function encodeArgsFor(ext) {
+  if (ext === ".wav") return ["-c:a", "pcm_s16le"];
+  if (ext === ".mp3") return ["-c:a", "libmp3lame", "-q:a", "2"];
+  if (ext === ".m4a" || ext === ".aac") return ["-c:a", "aac"];
+  if (ext === ".flac") return ["-c:a", "flac"];
+  return [
+    "-c:v",
+    "libx264",
+    "-preset",
+    "veryfast",
+    "-crf",
+    "18",
+    "-c:a",
+    "aac",
+    "-movflags",
+    "+faststart",
+  ];
+}
+
+function probeDuration(filePath) {
+  const raw = execFileSync(
+    "ffprobe",
+    [
+      "-v",
+      "error",
+      "-show_entries",
+      "format=duration",
+      "-of",
+      "default=noprint_wrappers=1:nokey=1",
+      "--",
+      filePath,
+    ],
+    { encoding: "utf8" },
+  );
+  const duration = Number(raw.trim());
+  if (!Number.isFinite(duration) || duration <= 0)
+    throw new Error(`could not probe duration: ${filePath}`);
+  return duration;
+}
+
+function escapeConcatPath(filePath) {
+  return filePath.replace(/'/g, "'\\''");
+}
+
+function sumDurations(segments) {
+  return segments.reduce((sum, segment) => sum + (segment.end - segment.start), 0);
+}
+
+function fmt(n) {
+  return round3(n)
+    .toFixed(3)
+    .replace(/\.?0+$/, "");
+}
+
+function round3(n) {
+  return Math.round(Number(n) * 1000) / 1000;
+}