XTTS-v2-argentinian-spanish Open-source Speech Generation Model - Clone Voice in 6 Seconds for Multiple Languages, Supports Argentine Spanish

XTTS V2 Argentinian Spanish

Developed by UNRN

ⓍTTS is a voice generation model that can clone a voice with just 6 seconds of audio and apply it to different languages, supporting Argentinian-accented Spanish.

Speech Synthesis SpanishOpen Source License:Other #Few-shot voice cloning #Argentinian Spanish #Multilingual speech synthesis

Downloads 16

Release Time : 7/23/2024

Model Overview

This model was trained by IdeaLab at the CITECCA center of the National University of Río Negro, fine-tuned to achieve Argentinian-accented Spanish voice generation.

Model Features

Rapid Voice Cloning

Only 6 seconds of audio clips are needed to clone the target voice.

Multilingual Support

The cloned voice can be applied to voice generation in different languages.

Accent-Specific Optimization

Specially optimized for Argentinian Spanish accents.

Efficient Training

Good results can be achieved without large amounts of training data.

Model Capabilities

Voice cloning

Text-to-Speech

Multilingual voice generation

Accent-specific speech synthesis

Use Cases

Speech Synthesis Applications

Personalized Voice Assistants

Create personalized Argentinian-accented voices for voice assistants.

Generates natural and fluent Argentinian Spanish speech.

Audio Content Creation

Quickly generate specific voices for audiobooks, podcasts, and other content.

Saves recording time and costs.

Accessibility Applications

Provide personalized voice reading experiences for visually impaired users.

Enhances user experience.

🚀 ⓍTTS 🇦🇷

ⓍTTS is a voice generation model that enables you to clone voices into different languages using just a 6 - second audio clip. There's no need for a large amount of training data spanning countless hours.

🚀 Quick Start

Using 🐸TTS Command line

 tts --model_name /path/to/xtts/ \
     --text "Che boludo, vamos a tomar unos mates." \
     --speaker_wav /path/to/target/speaker.wav \
     --language_idx es \
     --use_cuda true

Using the model directly

from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts

config = XttsConfig()
config.load_json("/path/to/xtts/config.json")
model = Xtts.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir="/path/to/xtts/", eval=True)
model.cuda()

outputs = model.synthesize(
    "Che boludo, vamos a tomar unos mates.",
    config,
    speaker_wav="/data/TTS-public/_refclips/3.wav",
    gpt_cond_len=3,
    language="es",
)

✨ Features

Voice cloning with just a 6 - second audio clip.
No need for excessive training data.
Fine - tuned for an Argentinian accent in Spanish.

📚 Documentation

Language

This model's Spanish language has been finetuned using ylacombe's google argentinian spanish dataset to achieve an Argentinian accent.

Training Parameters

batch_size=8,
grad_accum_steps=96,
batch_group_size=48,
eval_batch_size=8,
num_loader_workers=8,
eval_split_max_size=256,
optimizer="AdamW",
optimizer_wd_only_on_weights=True,
optimizer_params={"betas": [0.9, 0.96], "eps": 1e-8, "weight_decay": 1e-2},
lr=5e-06, 
lr_scheduler="MultiStepLR",
lr_scheduler_params={"milestones": [50000 * 18, 150000 * 18, 300000 * 18], "gamma": 0.5, "last_epoch": -1},

Model Information

Property	Details
Model Type	Voice generation model
Training Data	ylacombe/google-argentinian-spanish

📄 License

This model is licensed under Coqui Public Model License. There's a lot that goes into a license for generative models, and you can read more of the origin story of CPML here.

This model was trained by IdeaLab in CITECCA, in the Universidad Nacional de Rio Negro

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご