论文标题
PKWRAP：用于声学模型LF-MMI培训的Pytorch包装
Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models
论文作者
论文摘要
我们提供了一个简单的包装器，可用于使用Kaldi的LF-MMI训练框架在Pytorch中训练声学模型。包装器称为PKWRAP（Pytorch Kaldi包装器的简短形式），使用户能够利用Pytorch在设计模型体系结构时提供的灵活性。它将LF-MMI成本函数揭示为自动射击功能。 Kaldi的其他功能也已移植到Pytorch。这包括当多GPU环境不可用并用Kaldi中创建的图形解码时的并行训练能力。该软件包可在https://github.com/idiap/pkwrap上在github上找到。
We present a simple wrapper that is useful to train acoustic models in PyTorch using Kaldi's LF-MMI training framework. The wrapper, called pkwrap (short form of PyTorch kaldi wrapper), enables the user to utilize the flexibility provided by PyTorch in designing model architectures. It exposes the LF-MMI cost function as an autograd function. Other capabilities of Kaldi have also been ported to PyTorch. This includes the parallel training ability when multi-GPU environments are unavailable and decode with graphs created in Kaldi. The package is available on Github at https://github.com/idiap/pkwrap.
