You can deploy this model and start earning money today!

Aniket2003333333/
xtts-v2-child-voice-finetuned

Name: xtts-v2-child-voice-finetuned
Availability: InStock

Views

No views yet

XTTS v2 Fine-Tuned — Child Voice

This is a fine-tuned version of coqui/XTTS-v2 trained on the Samromur Children dataset to produce a child-like voice in English.

How to Use

pip install TTS==0.22.0 transformers==4.37.2 torch==2.1.0

python

import torch, soundfile as sf
from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts
from huggingface_hub import snapshot_download

# Download model
model_dir = snapshot_download("your-username/xtts-v2-child-voice-finetuned")

# Load
config = XttsConfig()
config.load_json(f"{model_dir}/config.json")
model = Xtts.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir=model_dir, eval=True)
model.cuda()

# Generate child voice speech
out = model.synthesize(
    "Hello! My name is Lily. I love playing with my toys!",
    config,
    speaker_wav=f"{model_dir}/reference_child.wav",
    language="en"
)
sf.write("output.wav", out["wav"], 24000)

Training Details

Base model: coqui/XTTS-v2
Dataset: Samromur Children (Icelandic child voices)
Epochs: 15
Fine-tuning type: GPT encoder fine-tuning
GPU: Tesla T4

Aniket2003333333/xtts-v2-child-voice-finetuned

XTTS v2 Fine-Tuned — Child Voice

How to Use

Training Details

Aniket2003333333/
xtts-v2-child-voice-finetuned