如何将输出添加到音频文件中？

Question

这是这个回购https://github.com/snakers4/silero-models#pytorch-1的代码吗?我想把声音输出到音频文件中，我该怎么做呢？

代码：

# V3
import torch

language = 'ru'
model_id = 'ru_v3'
sample_rate = 48000
speaker = 'ksenia'
device = torch.device('cpu')

model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models',
                                     model='silero_tts',
                                     language=language,
                                     speaker=model_id)
model.to(device)  # gpu or cpu

example_text = 'Привет, как делишки?'

audio = model.apply_tts(text=example_text,
                        speaker=speaker,
                        sample_rate=sample_rate)

我听说过，但这不适用于v_2或v_3

torchaudio.save('test_1.mp3',
                  audio[0].unsqueeze(0),
                  sample_rate=16000)

Answer 1

只要移除

所以这个看起来是这样的：

torchaudio.save('test_1.mp3',
                  audio.unsqueeze(0),
                  sample_rate=16000)