Configuration Parsing Warning:Invalid JSON for config file config.json

Okyeame TTS — Ghanaian English XTTS v2 Fine-tune

Fine-tuned XTTS v2 model for Ghanaian-accented English speech synthesis.

Usage

from TTS.api import TTS

tts = TTS()
tts.load_tts_model_by_path(
    model_path="model.pth",
    config_path="config.json"
)
tts.tts_to_file(
    text="Good morning, how are you doing today?",
    speaker_wav="reference.wav",
    language="en",
    file_path="output.wav"
)

Training Data

Trained on the Ghana English ASR 2700hrs dataset.

Model Details

Base model: XTTS v2 (Coqui)
Fine-tuning: GPT decoder layers
Sample rate: 22050 Hz (internal), 24000 Hz (output)

Downloads last month: 6

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support