將文本轉換為自然語音 使用 Zonos TTS

import torch
import torchaudio
from zonos.model import Zonos
from zonos.conditioning import make_cond_dict

# Initialize model
model = Zonos.from_pretrained("Zyphra/Zonos-v0.1-transformer", device="cuda")

# Load audio sample
wav, sampling_rate = torchaudio.load("assets/exampleaudio.mp3")
speaker = model.make_speaker_embedding(wav, sampling_rate)

# Generate speech
cond_dict = make_cond_dict(
    text="Hello, world!",
    speaker=speaker,
    language="en-us"
)
conditioning = model.prepare_conditioning(cond_dict)
codes = model.generate(conditioning)

# Save output
wavs = model.autoencoder.decode(codes).cpu()
torchaudio.save("sample.wav", wavs[0], model.autoencoder.sampling_rate)