数据集:

• KTH/匈牙利语单说话人语音合成

语言:

• 匈牙利语 (hu)

基础模型:

• 微软/speecht5_tts

许可证:

• MIT

任务标签:

• 文本转语音

这是一个针对匈牙利语的实验性SpeechT5微调模型。

from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
from IPython.display import Audio

processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
model = SpeechT5ForTextToSpeech.from_pretrained("GaborMadarasz/speecht5_tts_KTH_hu")
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan")

inputs = processor(text="自上次见到他们以来，已经过去了八年时光。", return_tensors="pt")

# 从数据集中加载包含说话人声音特征的xvector
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")
speaker_embeddings = torch.tensor(embeddings_dataset[7406]["xvector"]).unsqueeze(0)

speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)


# Jupyter音频播放
Audio(speech, rate=16000)