lasr:自动语音识别的PyTorch Lightning实现

上传者: 42144366 | 上传时间: 2022-11-04 09:33:45 | 文件大小: 52KB | 文件类型: ZIP
激光 闪电自动语音识别 一个基于PyTorch-Lightning的MIT许可ASR研究库,用于开发端到端ASR模型。 介绍 是用于高性能AI研究的轻量级包装器。 PyTorch非常易于使用,可以构建复杂的AI模型。 但是一旦研究变得复杂,并且诸如多GPU训练,16位精度和TPU训练之类的东西混在一起,用户很可能会引入错误。 PyTorch Lightning恰好解决了这个问题。 Lightning构造了您的PyTorch代码,因此它可以抽象出培训的详细信息。 这使AI研究具有可扩展性,并且可以快速迭代。 该项目是使用PyTorch Lightning实现asr项目的示例。 在这个项目中,我训练了一个模型,该模型包括一个带有联合CTC注意的构象编码器+ LSTM解码器。 所述LASR装置升ighthning一个utomatic小号peechřecognition。 我希望这可以成为那些研究

文件下载

资源详情

[{"title":"( 35 个子文件 52KB ) lasr:自动语音识别的PyTorch Lightning实现","children":[{"title":"lasr-main","children":[{"title":"setup.py <span style='color:#111;'> 1.70KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false},{"title":"dataset","children":[{"title":"prepare_libri.py <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"preprocess.py <span style='color:#111;'> 3.30KB </span>","children":null,"spread":false},{"title":"prepare-libri.sh <span style='color:#111;'> 2.13KB </span>","children":null,"spread":false}],"spread":true},{"title":"bin","children":[{"title":"main.py <span style='color:#111;'> 4.41KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 5.57KB </span>","children":null,"spread":false},{"title":"configs","children":[{"title":"data","children":[{"title":"default.yaml <span style='color:#111;'> 274B </span>","children":null,"spread":false}],"spread":true},{"title":"recognizer","children":[{"title":"default.yaml <span style='color:#111;'> 521B </span>","children":null,"spread":false}],"spread":true},{"title":"train.yaml <span style='color:#111;'> 72B </span>","children":null,"spread":false},{"title":"trainer","children":[{"title":"default.yaml <span style='color:#111;'> 170B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"lasr","children":[{"title":"data","children":[{"title":"data_loader.py <span style='color:#111;'> 6.56KB </span>","children":null,"spread":false},{"title":"lit_data_module.py <span style='color:#111;'> 4.87KB </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"embedding.py <span style='color:#111;'> 2.26KB </span>","children":null,"spread":false},{"title":"recognizer.py <span style='color:#111;'> 11.93KB </span>","children":null,"spread":false},{"title":"activation.py <span style='color:#111;'> 2.00KB </span>","children":null,"spread":false},{"title":"feed_forward.py <span style='color:#111;'> 2.53KB </span>","children":null,"spread":false},{"title":"attention.py <span style='color:#111;'> 11.51KB </span>","children":null,"spread":false},{"title":"modules.py <span style='color:#111;'> 3.46KB </span>","children":null,"spread":false},{"title":"decoder.py <span style='color:#111;'> 6.38KB </span>","children":null,"spread":false},{"title":"convolution.py <span style='color:#111;'> 7.33KB </span>","children":null,"spread":false},{"title":"encoder.py <span style='color:#111;'> 9.23KB </span>","children":null,"spread":false}],"spread":true},{"title":"vocabs","children":[{"title":"__init__.py <span style='color:#111;'> 1.48KB </span>","children":null,"spread":false},{"title":"librispeech.py <span style='color:#111;'> 2.16KB </span>","children":null,"spread":false}],"spread":true},{"title":"optim","children":[{"title":"__init__.py <span style='color:#111;'> 1.15KB </span>","children":null,"spread":false},{"title":"adamp.py <span style='color:#111;'> 3.59KB </span>","children":null,"spread":false},{"title":"lr_scheduler","children":[{"title":"__init__.py <span style='color:#111;'> 1.24KB </span>","children":null,"spread":false},{"title":"lr_scheduler.py <span style='color:#111;'> 1.64KB </span>","children":null,"spread":false},{"title":"tri_stage_lr_scheduler.py <span style='color:#111;'> 3.21KB </span>","children":null,"spread":false},{"title":"transformer_lr_scheduler.py <span style='color:#111;'> 2.72KB </span>","children":null,"spread":false}],"spread":false},{"title":"optimizer.py <span style='color:#111;'> 2.97KB </span>","children":null,"spread":false},{"title":"radam.py <span style='color:#111;'> 4.99KB </span>","children":null,"spread":false}],"spread":true},{"title":"criterioin","children":[{"title":"joint_ctc_cross_entropy.py <span style='color:#111;'> 2.55KB </span>","children":null,"spread":false}],"spread":true},{"title":"metric.py <span style='color:#111;'> 3.47KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"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