--- base_model: facebook/mms-tts-vie library_name: transformers.js pipeline_tag: text-to-speech tags: - text-to-audio --- https://huggingface.co/facebook/mms-tts-vie with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using: ```bash npm i @xenova/transformers ``` **Example:** Generate Vietnamese speech with `Xenova/mms-tts-vie`. ```js import { pipeline } from '@xenova/transformers'; // Create a text-to-speech pipeline const synthesizer = await pipeline('text-to-speech', 'Xenova/mms-tts-vie', { quantized: false, // Remove this line to use the quantized version (default) }); // Generate speech const output = await synthesizer('Xin chào'); console.log(output); // { // audio: Float32Array(20224) [ ... ], // sampling_rate: 16000 // } ``` Optionally, save the audio to a wav file (Node.js): ```js import wavefile from 'wavefile'; import fs from 'fs'; const wav = new wavefile.WaveFile(); wav.fromScratch(1, output.sampling_rate, '32f', output.audio); fs.writeFileSync('out.wav', wav.toBuffer()); ``` --- Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).