89 lines
3.4 KiB
JavaScript
89 lines
3.4 KiB
JavaScript
import {TtsSession} from '@mintplex-labs/piper-tts-web';
|
|
import {trackDownloadProgress} from './piper-download-progress.mjs';
|
|
import {localPiperModelUrl} from './piper-model-routing.mjs';
|
|
import {createOnnxWasmPaths} from './piper-onnx-config.mjs';
|
|
|
|
const VOICE_ID = 'sv_SE-nst-medium';
|
|
const ASSET_ROOT = '/static/piper-wasm-v1';
|
|
const localFetch = self.fetch.bind(self);
|
|
|
|
function reportStage(id, stage, details = {}) {
|
|
if (Number.isSafeInteger(id)) self.postMessage({id, type: 'progress', progress: {stage, ...details}});
|
|
}
|
|
|
|
// Keep the TTS library's OPFS cache logic, but serve models/config from the
|
|
// same-origin static asset service instead of its built-in external model URL.
|
|
self.fetch = async (resource, options) => {
|
|
const requestedUrl = resource instanceof Request ? resource.url : String(resource);
|
|
const localModelUrl = localPiperModelUrl(requestedUrl, self.location.origin);
|
|
if (!localModelUrl) {
|
|
const runtimeAsset = requestedUrl.includes('/static/piper-wasm-v1/onnx/');
|
|
const runtimeFile = runtimeAsset ? new URL(requestedUrl, self.location.origin).pathname.split('/').pop() : undefined;
|
|
if (activeRequestId && runtimeAsset) {
|
|
reportStage(activeRequestId, 'loading-runtime-assets', {file: runtimeFile});
|
|
}
|
|
const response = await localFetch(resource, options);
|
|
if (!activeRequestId || !runtimeAsset) return response;
|
|
reportStage(activeRequestId, 'reading-runtime-assets', {file: runtimeFile});
|
|
return trackDownloadProgress(response, {
|
|
id: activeRequestId,
|
|
asset: 'runtime',
|
|
file: runtimeFile,
|
|
postMessage: message => self.postMessage(message),
|
|
});
|
|
}
|
|
const isModel = localModelUrl.endsWith('.onnx');
|
|
if (activeRequestId) reportStage(activeRequestId, isModel ? 'loading-model' : 'loading-model-info');
|
|
const redirected = resource instanceof Request ? new Request(localModelUrl, resource) : localModelUrl;
|
|
const response = await localFetch(redirected, options);
|
|
if (!activeRequestId || !isModel) return response;
|
|
reportStage(activeRequestId, 'reading-model');
|
|
return trackDownloadProgress(response, {
|
|
id: activeRequestId,
|
|
postMessage: message => self.postMessage(message),
|
|
});
|
|
};
|
|
|
|
let sessionPromise;
|
|
let inferenceQueue = Promise.resolve();
|
|
let activeRequestId = null;
|
|
|
|
async function getSession() {
|
|
if (!sessionPromise) {
|
|
sessionPromise = TtsSession.create({
|
|
voiceId: VOICE_ID,
|
|
wasmPaths: {
|
|
onnxWasm: createOnnxWasmPaths(self.location.origin),
|
|
piperData: `${ASSET_ROOT}/piper/piper_phonemize.data`,
|
|
piperWasm: `${ASSET_ROOT}/piper/piper_phonemize.wasm`,
|
|
},
|
|
}).catch(error => {
|
|
sessionPromise = null;
|
|
throw error;
|
|
});
|
|
}
|
|
return sessionPromise;
|
|
}
|
|
|
|
async function synthesizeMessage(event) {
|
|
const {id, text} = event.data || {};
|
|
if (!Number.isSafeInteger(id) || typeof text !== 'string') return;
|
|
activeRequestId = id;
|
|
reportStage(id, 'loading-runtime');
|
|
try {
|
|
const session = await getSession();
|
|
reportStage(id, 'model-ready');
|
|
const blob = await session.predict(text);
|
|
const audio = await blob.arrayBuffer();
|
|
self.postMessage({id, type: 'audio', audio}, [audio]);
|
|
} catch (error) {
|
|
self.postMessage({id, type: 'error', error: String(error?.message || error)});
|
|
} finally {
|
|
activeRequestId = null;
|
|
}
|
|
}
|
|
|
|
self.addEventListener('message', event => {
|
|
inferenceQueue = inferenceQueue.then(() => synthesizeMessage(event));
|
|
});
|