PHBJT/dolly_thomas

XTTS v2 Fine-tuned Model

This is a fine-tuned version of the XTTS v2 text-to-speech model.

Model Details

• Base Model: XTTS v2
• Fine-tuning Date: 2024-12-02
• Repository: PHBJT/dolly_05

Usage

from TTS.api import TTS

# Initialize TTS with the custom model
tts = TTS(model_path="path_to_model_folder", config_path="path_to_config.json")

# Generate speech
tts.tts_to_file(text="Your text here", 
                speaker_wav="path_to_speaker.wav",
                language="en",
                file_path="output.wav")

Files

• model.pth: Main model weights
• config.json: Model configuration
• vocab.json: Tokenizer vocabulary
• mel_stats.pth: Mel-spectrogram statistics
• dvae.pth: Discrete VAE model