Skip to content

E2E Speech Recognition Toolkit with Hydra and Pytorch Lightning

Notifications You must be signed in to change notification settings

tuanio/asr-toolkit

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ASR E2E Toolkit

Encoder output

  • Input: inputs, input_lengths
  • Output: outputs, output_lengths

Decoder:

  • Input: targets, target_lengths, encoder_outputs (optional)

  • Output: decoder_outputs

  • Nếu có encoder_outputs thì mới sử dụng attention

Với mỗi lớp encoderdecoder thì đều phải có tham số output_dim

References

Variable

set HYDRA_FULL_ERROR=1

Run

  • python main.py -cp conf -cn configs

Training Template

Install package

conda create -n train_env -c pytorch-nightly -c nvidia -c pytorch -c conda-forge python=3.7 pytorch torchaudio cudatoolkit pandas numpy

Releases

No releases published

Packages

No packages published

Languages

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy