CODEWITHSUNDEEP
pythonpytorchtext-to-speech
SkruDJ
SkruDJ

Reputation: 167

Pytorch TTS how to add output to audio file?

Is this code from this repo https://github.com/snakers4/silero-models#pytorch-1 I'd like to output the voice to an audio file, how can I do that?

code:

# 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)

I heard about this, but this don't work with v_2 or v_3

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

Upvotes: 1

Views: 1659

Answers (1)

SkruDJ
SkruDJ

Reputation: 167

Just remove [0]

so this will be look like this:

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

Upvotes: 2

Related Questions