|
import torch |
|
import torchaudio |
|
import gradio as gr |
|
import matplotlib.pyplot as plt |
|
|
|
device="cpu" |
|
bundle = torchaudio.pipelines.TACOTRON2_WAVERNN_PHONE_LJSPEECH |
|
processor = bundle.get_text_processor() |
|
tacotron2 = bundle.get_tacotron2().to(device) |
|
|
|
|
|
|
|
waveglow = torch.hub.load( |
|
"NVIDIA/DeepLearningExamples:torchhub", |
|
"nvidia_waveglow", |
|
model_math="fp32", |
|
pretrained=False, |
|
) |
|
checkpoint = torch.hub.load_state_dict_from_url( |
|
"https://api.ngc.nvidia.com/v2/models/nvidia/waveglowpyt_fp32/versions/1/files/nvidia_waveglowpyt_fp32_20190306.pth", |
|
progress=False, |
|
map_location=device, |
|
) |
|
state_dict = {key.replace("module.", ""): value for key, value in checkpoint["state_dict"].items()} |
|
|
|
waveglow.load_state_dict(state_dict) |
|
waveglow = waveglow.remove_weightnorm(waveglow) |
|
waveglow = waveglow.to(device) |
|
waveglow.eval() |
|
|
|
def inference(text): |
|
|
|
with torch.inference_mode(): |
|
processed, lengths = processor(text) |
|
processed = processed.to(device) |
|
lengths = lengths.to(device) |
|
spec, _, _ = tacotron2.infer(processed, lengths) |
|
|
|
plt.imshow(spec[0].cpu().detach()) |
|
plt.axis('off') |
|
plt.savefig("test.png", bbox_inches='tight') |
|
|
|
with torch.no_grad(): |
|
waveforms = waveglow.infer(spec) |
|
|
|
torchaudio.save("output_waveglow.wav", waveforms[0:1].cpu(), sample_rate=22050) |
|
return "output_waveglow.wav","test.png" |
|
|
|
title="TACOTRON 2" |
|
description="Gradio demo for TACOTRON 2: The Tacotron 2 model for generating mel spectrograms from text. To use it, simply add you text or click on one of the examples to load them. Read more at the links below." |
|
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1712.05884' target='_blank'>Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions</a> | <a href='https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/Tacotron2' target='_blank'>Github Repo</a></p>" |
|
examples=[["life is like a box of chocolates"]] |
|
gr.Interface(inference,"text",[gr.outputs.Audio(type="file",label="Audio"),gr.outputs.Image(type="file",label="Spectrogram")],title=title,description=description,article=article,examples=examples).launch(enable_queue=True) |
