64 lines
1.7 KiB
JavaScript
64 lines
1.7 KiB
JavaScript
console.log("Initializing Kokoro TTS Worker");
|
|
|
|
import { KokoroTTS } from "https://cdn.jsdelivr.net/npm/kokoro-js@1.2.0/+esm";
|
|
async function detectWebGPU() {
|
|
try {
|
|
const adapter = await navigator.gpu.requestAdapter();
|
|
return !!adapter;
|
|
} catch (e) {
|
|
return false;
|
|
}
|
|
}
|
|
|
|
function blobToBase64(blob) {
|
|
return new Promise((resolve, _) => {
|
|
const reader = new FileReader();
|
|
reader.onloadend = () => resolve(reader.result);
|
|
reader.readAsDataURL(blob);
|
|
});
|
|
}
|
|
|
|
// Device detection
|
|
const device = (await detectWebGPU()) ? "webgpu" : "wasm";
|
|
self.postMessage({ status: "device", device });
|
|
|
|
console.log(`Detected device: ${device}`);
|
|
|
|
// Load the model
|
|
const model_id = "onnx-community/Kokoro-82M-v1.0-ONNX";
|
|
const tts = await KokoroTTS.from_pretrained(model_id, {
|
|
dtype: device === "wasm" ? "q8" : "fp32",
|
|
device,
|
|
progressCallback: (progress) => {
|
|
self.postMessage({ status: "progress", progress });
|
|
console.log(`Loading progress: ${progress * 100}%`);
|
|
},
|
|
});
|
|
|
|
console.log("Kokoro TTS model loaded successfully");
|
|
|
|
self.postMessage({ status: "ready", voices: tts.voices, device });
|
|
|
|
console.log("Available voices:", tts.voices);
|
|
|
|
// Listen for messages from the main thread
|
|
self.addEventListener("message", async (e) => {
|
|
const { text, voice } = e.data;
|
|
|
|
try {
|
|
// Generate speech
|
|
console.log(`Generating speech for text: "${text}" with voice: ${voice}`);
|
|
const audio = await tts.generate(text, { voice });
|
|
|
|
// Send the audio file back to the main thread
|
|
const blob = audio.toBlob();
|
|
self.postMessage({
|
|
status: "complete",
|
|
audio: await blobToBase64(blob),
|
|
text,
|
|
});
|
|
} catch (error) {
|
|
self.postMessage({ status: "error", error: error.message });
|
|
}
|
|
});
|