WeLe Agentic AI with Docker deployment

2026-08-28 08:50:08 +05:30
parent 586059b14f
commit 6bb0ef25ca
34 changed files with 2271 additions and 1343 deletions
@@ -0,0 +1,55 @@
+/* Does the locally-exported Tamil ONNX load and speak through Transformers.js? */
+import { pipeline, env } from '@huggingface/transformers';
+import fs from 'node:fs';
+
+// Load from the local folder, not the Hub.
+env.allowRemoteModels = false;
+env.localModelPath = './assets/tts';
+
+for (const dtype of ['q8', 'fp32']) {
+  try {
+    const t0 = performance.now();
+    const tts = await pipeline('text-to-speech', 'mms-tts-tam', { dtype });
+    const load = performance.now() - t0;
+
+    const TEXT = 'மூவாயிரம் நானூற்று இருபத்தேழு புதிய லீட்கள் உள்ளன.';
+    await tts(TEXT);                                  // warm
+
+    const t1 = performance.now();
+    const out = await tts(TEXT);
+    const ms = performance.now() - t1;
+    const audioMs = (out.audio.length / out.sampling_rate) * 1000;
+
+    console.log(
+      `${dtype.padEnd(5)} load ${(load / 1000).toFixed(1)}s | `
+      + `${ms.toFixed(0)}ms for ${audioMs.toFixed(0)}ms audio @ ${out.sampling_rate}Hz | `
+      + `RTF ${(ms / audioMs).toFixed(2)}x`,
+    );
+
+    // Non-silent output is the real proof the graph is wired correctly.
+    const peak = out.audio.reduce((m, v) => Math.max(m, Math.abs(v)), 0);
+    console.log(`      samples ${out.audio.length}, peak amplitude ${peak.toFixed(3)} ${peak > 0.01 ? '✅ audible' : '⚠️ SILENT'}`);
+
+    if (dtype === 'q8') {
+      const wav = toWav(out.audio, out.sampling_rate);
+      fs.writeFileSync('scripts/tamil-sample.wav', wav);
+      console.log('      wrote scripts/tamil-sample.wav — play it to judge quality');
+    }
+  } catch (e) {
+    console.log(`${dtype.padEnd(5)} FAILED: ${e.message.slice(0, 160)}`);
+  }
+}
+
+function toWav(samples, rate) {
+  const buf = Buffer.alloc(44 + samples.length * 2);
+  buf.write('RIFF', 0); buf.writeUInt32LE(36 + samples.length * 2, 4); buf.write('WAVE', 8);
+  buf.write('fmt ', 12); buf.writeUInt32LE(16, 16); buf.writeUInt16LE(1, 20); buf.writeUInt16LE(1, 22);
+  buf.writeUInt32LE(rate, 24); buf.writeUInt32LE(rate * 2, 28); buf.writeUInt16LE(2, 32); buf.writeUInt16LE(16, 34);
+  buf.write('data', 36); buf.writeUInt32LE(samples.length * 2, 40);
+  for (let i = 0; i < samples.length; i++) {
+    const s = Math.max(-1, Math.min(1, samples[i]));
+    buf.writeInt16LE(s < 0 ? s * 0x8000 : s * 0x7fff, 44 + i * 2);
+  }
+  return buf;
+}
+process.exit(0);