Vocoder with HiFIGAN trained on custom German dataset
This repository provides all the necessary tools for using a HiFIGAN vocoder trained on a generated German dataset using mp3_to_training_data.
The pre-trained model (8 epochs so far) takes in input a spectrogram and produces a waveform in output. Typically, a vocoder is used after a TTS model that converts an input text into a spectrogram.
How to use
Install speechbrain.
pip install speechbrain
Use a TTS model (e.g. tts-tacotron-german), generate a spectrogram and convert it to audio.
import torchaudio
from speechbrain.pretrained import Tacotron2
from speechbrain.pretrained import HIFIGAN
tacotron2 = Tacotron2.from_hparams(source="padmalcom/tts-tacotron2-german", savedir="tmpdir_tts")
hifi_gan = HIFIGAN.from_hparams(source="padmalcom/tts-hifigan-german", savedir="tmpdir_vocoder")
mel_output, mel_length, alignment = tacotron2.encode_text("Mary had a little lamb")
waveforms = hifi_gan.decode_batch(mel_output)
torchaudio.save('example_TTS.wav',waveforms.squeeze(1), 22050)
Inference on GPU
To perform inference on the GPU, add run_opts={"device":"cuda"}
when calling the from_hparams
method.
数据统计
数据评估
本站OpenI提供的padmalcom/tts-hifigan-german都来源于网络,不保证外部链接的准确性和完整性,同时,对于该外部链接的指向,不由OpenI实际控制,在2023年 5月 26日 下午6:12收录时,该网页上的内容,都属于合规合法,后期网页的内容如出现违规,可以直接联系网站管理员进行删除,OpenI不承担任何责任。