@drakulavich/parakeet-cli 0.2.0 → 0.3.0

package/package.json

@@ -1,11 +1,15 @@
 {
   "name": "@drakulavich/parakeet-cli",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "Fast multilingual speech-to-text CLI powered by NVIDIA Parakeet ONNX models",
   "type": "module",
   "bin": {
     "parakeet": "bin/parakeet.js"
   },
+  "exports": {
+    ".": "./src/cli.ts",
+    "./core": "./src/lib.ts"
+  },
   "files": [
     "bin/",
     "src/",

package/src/__tests__/lib.test.ts

@@ -0,0 +1,12 @@
+import { describe, expect, it } from "bun:test";
+import { transcribe } from "../lib";
+
+describe("lib API", () => {
+  it("exports transcribe function", () => {
+    expect(typeof transcribe).toBe("function");
+  });
+
+  it("rejects missing file", async () => {
+    await expect(transcribe("/nonexistent/audio.wav")).rejects.toThrow("File not found");
+  });
+});

package/src/cli.ts

@@ -1,7 +1,6 @@
 #!/usr/bin/env bun
 
-import { existsSync } from "fs";
-import { transcribe } from "./transcribe";
+import { transcribe } from "./lib";
 
 async function main(): Promise<void> {
   const args = process.argv.slice(2);
@@ -20,11 +19,6 @@ async function main(): Promise<void> {
     process.exit(1);
   }
 
-  if (!existsSync(file)) {
-    console.error(`Error: file not found: ${file}`);
-    process.exit(1);
-  }
-
   try {
     const text = await transcribe(file, { noCache });
     if (text) process.stdout.write(text + "\n");

package/src/lib.ts

@@ -0,0 +1,23 @@
+import { existsSync } from "fs";
+import { transcribe as internalTranscribe } from "./transcribe";
+
+export interface TranscribeOptions {
+  beamWidth?: number;
+  noCache?: boolean;
+  modelDir?: string;
+}
+
+export async function transcribe(
+  audioPath: string,
+  options: TranscribeOptions = {},
+): Promise<string> {
+  if (!existsSync(audioPath)) {
+    throw new Error(`File not found: ${audioPath}`);
+  }
+
+  return internalTranscribe(audioPath, {
+    noCache: options.noCache ?? false,
+    beamWidth: options.beamWidth,
+    modelDir: options.modelDir,
+  });
+}

package/src/models.ts

@@ -16,13 +16,13 @@ export function getModelDir(): string {
   return join(homedir(), ".cache", "parakeet", "v3");
 }
 
-export function isModelCached(): boolean {
-  const dir = getModelDir();
-  return MODEL_FILES.every((f) => existsSync(join(dir, f)));
+export function isModelCached(dir?: string): boolean {
+  const d = dir ?? getModelDir();
+  return MODEL_FILES.every((f) => existsSync(join(d, f)));
 }
 
-export async function ensureModel(noCache = false): Promise<string> {
-  const dir = getModelDir();
+export async function ensureModel(noCache = false, modelDir?: string): Promise<string> {
+  const dir = modelDir ?? getModelDir();
 
   if (!noCache && isModelCached()) {
     return dir;

package/src/transcribe.ts

@@ -26,6 +26,8 @@ const DECODER_HIDDEN = 640;
 
 export interface TranscribeOptions {
   noCache?: boolean;
+  beamWidth?: number;
+  modelDir?: string;
 }
 
 // Minimum 0.1s of audio at 16kHz to produce meaningful output
@@ -39,7 +41,8 @@ export async function transcribe(audioPath: string, opts: TranscribeOptions = {}
   }
 
   const noCache = opts.noCache ?? false;
-  const modelDir = await ensureModel(noCache);
+  const beamWidth = opts.beamWidth ?? 4;
+  const modelDir = await ensureModel(noCache, opts.modelDir);
   const tokenizer = await Tokenizer.fromFile(join(modelDir, "vocab.txt"));
 
   await initPreprocessor(modelDir);
@@ -63,6 +66,6 @@ export async function transcribe(audioPath: string, opts: TranscribeOptions = {}
     DECODER_HIDDEN,
   );
 
-  const tokens = await beamDecode(session, encodedLength, transposed, D);
+  const tokens = await beamDecode(session, encodedLength, transposed, D, beamWidth);
   return tokenizer.detokenize(tokens);
 }