mirror of https://github.com/babysor/MockingBird.git synced 2024-03-22 13:11:31 +08:00

History

flysmart 86ea11affd Fre-GAN (#544 ) * 替换了vocoder * 修改了vocoder_train * 减谱法 * 美化UI；语音增强；MFCC特征可视化 * 修复了训练fregan模型时的报错 * 增加了可以分析音频特征的独立文件 * 现已支持Fre-GAN声码器的训练 * 修复了训练fregan时保存模型的BUG * 删除了无用的文件 * 优化了识别声码器模型的方式		2022-05-09 13:22:55 +08:00
..
LJSpeech-1.1	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
.gitignore	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
config.json	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
discriminator.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
dwt.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
generator.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
inference.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
LICENSE	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
loss.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
meldataset.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
modules.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
README.md	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
requirements.txt	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
stft_loss.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
train.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +08:00
utils.py	Fre-GAN (#544 )	2022-05-09 13:22:55 +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.

README.md

Fre-GAN Vocoder

Training:

Citation:

Note

References: