@drakulavich/parakeet-cli 0.6.0 → 0.7.0

package/README.md

@@ -1,10 +1,9 @@
 # 🦜 parakeet-cli
 
-[![npm version](https://img.shields.io/npm/v/@drakulavich/parakeet-cli)](https://www.npmjs.com/package/@drakulavich/parakeet-cli)
 [![CI](https://github.com/drakulavich/parakeet-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/drakulavich/parakeet-cli/actions/workflows/ci.yml)
+[![npm version](https://img.shields.io/npm/v/@drakulavich/parakeet-cli)](https://www.npmjs.com/package/@drakulavich/parakeet-cli)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![Bun](https://img.shields.io/badge/runtime-Bun-f9f1e1?logo=bun)](https://bun.sh)
-[![Test Report](https://img.shields.io/badge/Test_Report-Allure-orange)](https://drakulavich.github.io/parakeet-cli/reports/allure)
 
 Fast local speech-to-text. 25 languages. ~18x faster than Whisper on Apple Silicon.
 
@@ -39,21 +38,31 @@ Stdout: transcript. Stderr: errors. Pipe-friendly.
 - [ffmpeg](https://ffmpeg.org) in PATH (ONNX backend only)
 - ~3GB disk (ONNX models)
 
-## Supported Languages
+## Benchmark
 
-:bulgaria: Bulgarian, :croatia: Croatian, :czech_republic: Czech, :denmark: Danish, :netherlands: Dutch, :gb: English, :estonia: Estonian, :finland: Finnish, :fr: French, :de: German, :greece: Greek, :hungary: Hungarian, :it: Italian, :latvia: Latvian, :lithuania: Lithuanian, :malta: Maltese, :poland: Polish, :portugal: Portuguese, :romania: Romanian, :ru: Russian, :slovakia: Slovak, :slovenia: Slovenian, :es: Spanish, :sweden: Swedish, :ukraine: Ukrainian
+> **~18x faster than Whisper** on Apple Silicon (CoreML)
 
-## Benchmark
+<details>
+<summary>MacBook Pro M3 Pro — 10 Russian voice messages</summary>
 
-MacBook Pro M3 Pro — 10 Russian voice messages:
+```
+faster-whisper (CPU):  35.3s  ██████████████████████████████████████ 
+Parakeet (CoreML):      1.9s  ██
+```
 
-| | faster-whisper (CPU) | Parakeet (CoreML) |
-|---|---|---|
-| **Total** | 35.3s | 1.9s |
-| **Speed** | | **~18x faster** |
+| | faster-whisper | Parakeet | Speedup |
+|---|---|---|---|
+| Apple Silicon (CoreML) | 35.3s | **1.9s** | **~18x** |
+| Linux CI (ONNX) | 79.2s | **45.4s** | **~1.7x** |
+
+</details>
 
 Full results with transcripts: [BENCHMARK.md](BENCHMARK.md)
 
+## Supported Languages
+
+:bulgaria: Bulgarian, :croatia: Croatian, :czech_republic: Czech, :denmark: Danish, :netherlands: Dutch, :gb: English, :estonia: Estonian, :finland: Finnish, :fr: French, :de: German, :greece: Greek, :hungary: Hungarian, :it: Italian, :latvia: Latvian, :lithuania: Lithuanian, :malta: Maltese, :poland: Polish, :portugal: Portuguese, :romania: Romanian, :ru: Russian, :slovakia: Slovak, :slovenia: Slovenian, :es: Spanish, :sweden: Swedish, :ukraine: Ukrainian
+
 ## How It Works
 
 ```
@@ -83,6 +92,10 @@ Drop-in replacement for OpenClaw voice processing — no API keys, runs locally.
 }
 ```
 
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md).
+
 ## License
 
 MIT

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@drakulavich/parakeet-cli",
-  "version": "0.6.0",
-  "description": "Fast multilingual speech-to-text CLI powered by NVIDIA Parakeet ONNX models",
+  "version": "0.7.0",
+  "description": "Fast local speech-to-text CLI. CoreML on Apple Silicon, ONNX on CPU. 25 languages.",
   "type": "module",
   "bin": {
     "parakeet": "bin/parakeet.js"
@@ -49,6 +49,7 @@
   },
   "devDependencies": {
     "@types/bun": "latest",
+    "fast-xml-parser": "^5.5.10",
     "typescript": "^6.0.2"
   },
   "dependencies": {

package/src/models.ts

@@ -53,7 +53,7 @@ export async function downloadModel(noCache = false, modelDir?: string): Promise
   const dir = modelDir ?? getModelDir();
 
   if (!noCache && isModelCached(dir)) {
-    console.error("Model already downloaded.");
+    console.log("Model already downloaded.");
     return dir;
   }
 
@@ -67,21 +67,50 @@ export async function downloadModel(noCache = false, modelDir?: string): Promise
 
     console.error(`Downloading ${file}...`);
 
-    const res = await fetch(url, { redirect: "follow" });
+    let res: Response;
+    try {
+      res = await fetch(url, { redirect: "follow" });
+    } catch (e) {
+      throw new Error(`failed to fetch ${file}: ${e instanceof Error ? e.message : e}`);
+    }
 
     if (!res.ok) {
-      throw new Error(`failed to download model: ${url} (${res.status})`);
+      throw new Error(`failed to download ${file}: HTTP ${res.status}`);
+    }
+
+    if (!res.body) {
+      throw new Error(`empty response body for ${file}`);
+    }
+
+    const writer = Bun.file(dest).writer();
+    let bytes = 0;
+    try {
+      for await (const chunk of res.body) {
+        writer.write(chunk);
+        bytes += chunk.length;
+      }
+    } finally {
+      writer.end();
     }
 
-    await Bun.write(dest, res);
+    if (bytes === 0) {
+      throw new Error(`downloaded 0 bytes for ${file}`);
+    }
   }
 
-  console.error("Model downloaded successfully.");
+  console.log("Model downloaded successfully.");
   return dir;
 }
 
+const COREML_BINARY_NAME = "parakeet-coreml-darwin-arm64";
+const GITHUB_REPO = "drakulavich/parakeet-cli";
+
 export function getCoreMLDownloadURL(version: string): string {
-  return `https://github.com/drakulavich/parakeet-cli/releases/download/v${version}/parakeet-coreml-darwin-arm64`;
+  return `https://github.com/${GITHUB_REPO}/releases/download/v${version}/${COREML_BINARY_NAME}`;
+}
+
+export function getCoreMLLatestDownloadURL(): string {
+  return `https://github.com/${GITHUB_REPO}/releases/latest/download/${COREML_BINARY_NAME}`;
 }
 
 export async function downloadCoreML(noCache = false): Promise<string> {
@@ -89,19 +118,32 @@ export async function downloadCoreML(noCache = false): Promise<string> {
   const binPath = getCoreMLBinPath();
 
   if (!noCache && existsSync(binPath)) {
-    console.error("CoreML backend already installed.");
-    return binPath;
+    // Binary exists — ensure models are also downloaded
+    const checkProc = Bun.spawnSync([binPath, "--download-only"], {
+      stdout: "pipe",
+      stderr: "pipe",
+    });
+    if (checkProc.exitCode === 0) {
+      console.log("CoreML backend already installed.");
+      return binPath;
+    }
+    // Models missing — continue to re-download
   }
 
-  const pkg = await Bun.file(new URL("../package.json", import.meta.url)).json();
-  const url = getCoreMLDownloadURL(pkg.version);
-
+  // Try latest release first, fall back to version-specific
+  const latestUrl = getCoreMLLatestDownloadURL();
   console.error("Downloading parakeet-coreml binary...");
 
-  const res = await fetch(url, { redirect: "follow" });
+  let res = await fetch(latestUrl, { redirect: "follow" });
+
+  if (!res.ok) {
+    const pkg = await Bun.file(new URL("../package.json", import.meta.url)).json();
+    const versionUrl = getCoreMLDownloadURL(pkg.version);
+    res = await fetch(versionUrl, { redirect: "follow" });
+  }
 
   if (!res.ok) {
-    throw new Error(`Failed to download CoreML binary: ${url} (${res.status})`);
+    throw new Error(`Failed to download CoreML binary (HTTP ${res.status}). No release found with ${COREML_BINARY_NAME}.`);
   }
 
   mkdirSync(dirname(binPath), { recursive: true });
@@ -110,6 +152,17 @@ export async function downloadCoreML(noCache = false): Promise<string> {
 
   chmodSync(binPath, 0o755);
 
-  console.error("CoreML backend installed successfully.");
+  // Download CoreML model files (first transcription would be slow without this)
+  console.error("Downloading CoreML models...");
+  const downloadProc = Bun.spawnSync([binPath, "--download-only"], {
+    stdout: "inherit",
+    stderr: "inherit",
+  });
+
+  if (downloadProc.exitCode !== 0) {
+    throw new Error("Failed to download CoreML models");
+  }
+
+  console.log("CoreML backend installed successfully.");
   return binPath;
 }