About loading pretrained models

Alexander-H-Liu / End-to-end-ASR-Pytorch

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

MIT License

1.19k stars 318 forks source link

About loading pretrained models #24

Closed atliSig closed 5 years ago

atliSig commented 5 years ago

Hey.

Is there any good reason for not implementing loading pre-trained model (reference) ?

Afaik loading a pre trained model is as easy as self.asr = torch.load('./results/<exp_name>/asr). Is that assumption wrong?