Mms Spa Finetuned Colombian Monospeaker

🚀 Transformers Text-to-Speech Model

This project provides a fine-tuned text-to-speech model based on the Transformers library, enabling high-quality Spanish speech synthesis.

🚀 Quick Start

This is a fine-tuned version of the Spanish version of Massively Multilingual Speech (MMS) models. These are light-weight, low-latency TTS models based on the VITS architecture.

It was trained in around 20 minutes with as little as 80 to 150 samples on this Colombian Spanish dataset. The training recipe is available in this GitHub repository: ylacombe/finetune-hf-vits.

✨ Features

• Fine-tuned Model: Based on the Spanish version of MMS models, fine-tuned for Colombian Spanish.
• Efficient Training: Can be trained in a short time with a small number of samples.
• Multi-platform Support: Supports both Python (transformers) and JavaScript (transformers.js).

📦 Installation

If you want to use the JavaScript library Transformers.js, you can install it from NPM using the following command:

npm i @xenova/transformers

💻 Usage Examples

Basic Usage (Python)

from transformers import pipeline
import scipy

model_id = "ylacombe/mms-spa-finetuned-colombian-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"])

Advanced Usage (JavaScript)

Generate Spanish speech with ylacombe/mms-spa-finetuned-colombian-monospeaker.

import { pipeline } from '@xenova/transformers';

// Create a text-to-speech pipeline
const synthesizer = await pipeline('text-to-speech', 'ylacombe/mms-spa-finetuned-colombian-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):

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());

You can listen to an example audio here:

📄 License

This project is licensed under the cc-by-nc-4.0 license.

📚 Documentation

Model Information