XTTS-v2-argentinian-spanish Open-source Voice Generation Model - Clone Voices in 6-second Audio, No Massive Training Required for Cross-lingual Applications

XTTS V2 Argentinian Spanish

Developed by marianbasti

ⓍTTS is a speech generation model that can clone voices with just 6 seconds of audio and apply them to different languages. No need for hours of extensive training data.

Speech Synthesis SpanishOpen Source License:Other #6-second voice cloning #Argentinian Spanish #Multilingual speech synthesis

Downloads 44

Release Time : 7/2/2024

Model Overview

ⓍTTS is a speech generation model capable of voice cloning with minimal audio samples, specifically optimized for Argentinian Spanish accents.

Model Features

Rapid Voice Cloning

Clone target voices with just 6 seconds of audio samples

Multilingual Support

Apply cloned voices to speech generation in different languages

Argentinian Accent Optimization

Fine-tuned specifically for Argentinian Spanish accents

Model Capabilities

Voice cloning

Text-to-Speech

Multilingual speech generation

Use Cases

Speech Synthesis

Personalized Voice Assistants

Create personalized Argentinian Spanish voices for voice assistants

Generate natural and fluent Argentinian-accented speech

Audio Content Creation

Quickly generate Argentinian Spanish audio content in different styles

Obtain high-quality voice output without professional recording

🚀 ⓍTTS 🇦🇷

ⓍTTS is a voice generation model that enables voice cloning across different languages using just a 6 - second audio clip. It eliminates the need for extensive training data spanning numerous hours.

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

🚀 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.
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},

📄 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.

Property	Details
Model Type	Text - to - Speech
Training Data	ylacombe/google-argentinian-spanish
License	Coqui Public Model License

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