README.md

---
library_name: transformers
pipeline_tag: text-to-speech
tags:
- transformers.js
- mms
- vits
license: cc-by-nc-4.0
datasets:
- ylacombe/google-marathi
language:
- mr
---

## Model

This is a finetuned version of the [Marathi version](https://huggingface.co/facebook/mms-tts-mar) of Massively Multilingual Speech (MMS) models, which are light-weight, low-latency TTS models based on the [VITS architecture](https://huggingface.co/docs/transformers/model_doc/vits).

It was trained in around **20 minutes** with as little as **80 to 150 samples**, on this [Marathi dataset](https://huggingface.co/datasets/ylacombe/google-marathi).

Training recipe available in this [github repository: **ylacombe/finetune-hf-vits**](https://github.com/ylacombe/finetune-hf-vits).


## Usage

### Transformers

```python
from transformers import pipeline
import scipy

model_id = "ylacombe/mms-mar-finetuned-monospeaker"
synthesiser = pipeline("text-to-speech", model_id) # add device=0 if you want to use a GPU

speech = synthesiser("Hola, ¿cómo estás hoy?")

scipy.io.wavfile.write("finetuned_output.wav", rate=speech["sampling_rate"], data=speech["audio"])
```

### 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 Marathi speech with `ylacombe/mms-mar-finetuned-monospeaker`.
```js
import { pipeline } from '@xenova/transformers';

// Create a text-to-speech pipeline
const synthesizer = await pipeline('text-to-speech', 'ylacombe/mms-mar-finetuned-monospeaker', {
    quantized: false, // Remove this line to use the quantized version (default)
});

// Generate speech
const output = await synthesizer('Hola, ¿cómo estás hoy?');
console.log(output);
// {
//   audio: Float32Array(69888) [ ... ],
//   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());
```