HiFi-GAN:HiFi-GAN

上传者: 42173218 | 上传时间: 2022-04-29 21:20:55 | 文件大小: 420KB | 文件类型: ZIP
HiFi-GAN:高效,高保真语音合成的生成对抗网络 非官方PyTorch实现。 HiFi-GAN: 先决条件 在Python 3.6上测试 pip install -r requirements.txt 准备数据集 下载数据集进行培训。 这可以是任何采样率为22050Hz的wav文件。 (例如,在纸上使用了LJSpeech) 预处理: python preprocess.py -c config/default.yaml -d [data's root path] 编辑配置yaml文件 火车和张量板 python trainer.py -c [config yaml file] -n [name of the run] cp config/default.yaml config/config.yaml ,然后编辑config.yaml 将训练/验证文件的根路径写下到第二/第三行。

文件下载

资源详情

[{"title":"( 30 个子文件 420KB ) HiFi-GAN:HiFi-GAN","children":[{"title":"HiFi-GAN-main","children":[{"title":"inference.py <span style='color:#111;'> 2.12KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"train.py <span style='color:#111;'> 10.45KB </span>","children":null,"spread":false},{"title":"stft.py <span style='color:#111;'> 7.42KB </span>","children":null,"spread":false},{"title":"hparams.py <span style='color:#111;'> 1.73KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 831B </span>","children":null,"spread":false},{"title":"audio_processing.py <span style='color:#111;'> 2.54KB </span>","children":null,"spread":false},{"title":"writer.py <span style='color:#111;'> 2.84KB </span>","children":null,"spread":false},{"title":"stft_loss.py <span style='color:#111;'> 4.83KB </span>","children":null,"spread":false},{"title":"plotting.py <span style='color:#111;'> 1.36KB </span>","children":null,"spread":false},{"title":"validation.py <span style='color:#111;'> 3.62KB </span>","children":null,"spread":false}],"spread":true},{"title":"export_torchscript.py <span style='color:#111;'> 2.15KB </span>","children":null,"spread":false},{"title":"configs","children":[{"title":"default.yaml <span style='color:#111;'> 1.72KB </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"mrf.py <span style='color:#111;'> 712B </span>","children":null,"spread":false},{"title":"mpd.py <span style='color:#111;'> 892B </span>","children":null,"spread":false},{"title":"resstack.py <span style='color:#111;'> 1.34KB </span>","children":null,"spread":false},{"title":"generator.py <span style='color:#111;'> 20.50KB </span>","children":null,"spread":false},{"title":"discriminator.py <span style='color:#111;'> 2.54KB </span>","children":null,"spread":false},{"title":"period_discriminator.py <span style='color:#111;'> 1.62KB </span>","children":null,"spread":false},{"title":"multiscale.py <span style='color:#111;'> 6.09KB </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 79B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"dataloader.py <span style='color:#111;'> 2.56KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"assets","children":[{"title":"fig2.JPG <span style='color:#111;'> 116.25KB </span>","children":null,"spread":false},{"title":"fig3.JPG <span style='color:#111;'> 215.81KB </span>","children":null,"spread":false},{"title":"fig1.JPG <span style='color:#111;'> 220.74KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 1.30KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false},{"title":"denoiser.py <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false},{"title":"preprocess.py <span style='color:#111;'> 1.98KB </span>","children":null,"spread":false},{"title":"trainer.py <span style='color:#111;'> 1.83KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明