StarMirror/MockingBird
1
0
Fork 0
mirror of https://github.com/babysor/MockingBird.git synced 2024-03-22 13:11:31 +08:00
Code Issues Projects Releases Wiki Activity
350b190662
MockingBird/vocoder/fregan
History
flysmart 350b190662
Solved the problem that the existing model could not be loaded when training the GAN model (#549) 
* The new vocoder Fre-GAN is now supported

* Improved some fregan details

* Fixed the problem that the existing model could not be loaded to continue training when training GAN

* Updated reference papers
2022-05-13 13:41:03 +08:00
..
.gitignore The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
config.json The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
discriminator.py The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
dwt.py The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
generator.py The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
inference.py The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
LICENSE The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
loss.py The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
meldataset.py The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
modules.py The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
README.md The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
requirements.txt The new vocoder Fre-GAN is now supported (#546) 2022-05-12 12:27:17 +08:00
train.py Solved the problem that the existing model could not be loaded when training the GAN model (#549) 2022-05-13 13:41:03 +08:00
utils.py Solved the problem that the existing model could not be loaded when training the GAN model (#549) 2022-05-13 13:41:03 +08:00

README.md

Fre-GAN Vocoder

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

Training:

python train.py --config config.json

Citation:

@misc{kim2021fregan,
      title={Fre-GAN: Adversarial Frequency-consistent Audio Synthesis}, 
      author={Ji-Hoon Kim and Sang-Hoon Lee and Ji-Hyun Lee and Seong-Whan Lee},
      year={2021},
      eprint={2106.02297},
      archivePrefix={arXiv},
      primaryClass={eess.AS}
}

Note

  • For more complete and end to end Voice cloning or Text to Speech (TTS) toolbox please visit Deepsync Technologies.

References: