Spaces:
Build error
Build error
import gradio as gr | |
import time | |
import torch | |
import scipy.io.wavfile | |
from espnet2.bin.tts_inference import Text2Speech | |
from espnet2.utils.types import str_or_none | |
tagen = "https://huggingface.co/wietsedv/tacotron2-gronings/resolve/main/tts_ljspeech_finetune_tacotron2.v5_train.loss.ave.zip" | |
vocoder_tagen = "parallel_wavegan/ljspeech_parallel_wavegan.v3" | |
text2speechen = Text2Speech.from_pretrained( | |
model_tag=str_or_none(tagen), | |
vocoder_tag=str_or_none(vocoder_tagen), | |
device="cpu", | |
threshold=0.5, | |
minlenratio=0.0, | |
maxlenratio=10.0, | |
use_att_constraint=True, | |
backward_window=1, | |
forward_window=4, | |
) | |
def inference(text,lang): | |
with torch.no_grad(): | |
if lang == "gronings": | |
wav = text2speechen(text)["wav"] | |
scipy.io.wavfile.write("out.wav",text2speechen.fs , wav.view(-1).cpu().numpy()) | |
return "out.wav" | |
title = "ESPnet2-TTS" | |
description = "Gradio demo for ESPnet2-TTS: Extending the Edge of TTS Research. To use it, simply add your audio, or click 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/2110.07840' target='_blank'>ESPnet2-TTS: Extending the Edge of TTS Research</a> | <a href='https://github.com/espnet/espnet' target='_blank'>Github Repo</a></p>" | |
examples=[['This paper describes ESPnet2-TTS, an end-to-end text-to-speech (E2E-TTS) toolkit. ESPnet2-TTS extends our earlier version, ESPnet-TTS, by adding many new features, including: on-the-fly flexible pre-processing, joint training with neural vocoders, and state-of-the-art TTS models with extensions like full-band E2E text-to-waveform modeling, which simplify the training pipeline and further enhance TTS performance. The unified design of our recipes enables users to quickly reproduce state-of-the-art E2E-TTS results',"english"]] | |
gr.Interface( | |
inference, | |
[gr.inputs.Textbox(label="input text",lines=10),gr.inputs.Radio(choices=["gronings"], type="value", default="gronings", label="language")], | |
gr.outputs.Audio(type="file", label="Output"), | |
title=title, | |
description=description, | |
article=article, | |
enable_queue=True, | |
examples=examples | |
).launch(debug=True) |