CaroTTS-60M-DE-Caro

import torch
import soundfile as sf
from nemo.collections.tts.models.fastpitch import FastPitchModel
from nemo.collections.tts.models.hifigan import HifiGanModel

# Load models
device = "cuda" if torch.cuda.is_available() else "cpu"
fastpitch = FastPitchModel.restore_from("Caro_fastpitch.nemo", map_location=device).eval()
hifigan = HifiGanModel.restore_from("Caro_hifigan.nemo", map_location=device).eval()

# Prepare text
text = "Guten Tag. Herzlich Willkommen zu dieser Demonstration."

with torch.inference_mode():
    # Parse and generate
    parsed_text = fastpitch.parse(text)
    spec = fastpitch.generate_spectrogram(tokens=parsed_text)
    audio = hifigan.convert_spectrogram_to_audio(spec=spec)

    # Save audio (44.1kHz sample rate)
    sf.write("output.wav", audio.squeeze().cpu().numpy(), 44100)