Speech-Transformer | PyTorch re-implementation of Speech-Transformer | Speech library

by foamliu Python Version: v1.0 License: MIT

X-Ray Key Features Code Snippets(3)Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | Speech-Transformer Summary

Speech-Transformer is a Python library typically used in Artificial Intelligence, Speech, Deep Learning, Pytorch, Transformer applications. Speech-Transformer has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can download it from GitHub.

This is a PyTorch re-implementation of Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition.

Support

Quality

Security

License

Reuse

Support

Speech-Transformer has a low active ecosystem.

It has 67 star(s) with 17 fork(s). There are 3 watchers for this library.

It had no major release in the last 12 months.

There are 1 open issues and 12 have been closed. On average issues are closed in 39 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of Speech-Transformer is v1.0

Quality

Speech-Transformer has 0 bugs and 21 code smells.

Security

Speech-Transformer has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

Speech-Transformer code analysis shows 0 unresolved vulnerabilities.

There are 3 security hotspots that need review.

License

Speech-Transformer is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

Speech-Transformer releases are available to install and integrate.

Build file is available. You can build the component from source.

Installation instructions are not available. Examples and code snippets are available.

Speech-Transformer saves you 507 person hours of effort in developing the same functionality from scratch.

It has 1191 lines of code, 69 functions and 22 files.

It has medium code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed Speech-Transformer and discovered the below as its top functions. This is intended to give you an instant insight into Speech-Transformer implemented functionality, and help decide if they suit your requirements.

Train the network
Calculate loss
Calculate the Calculation of the loss
Update statistics
Train the model
Augment the spectrogram using a time warping
Adds zero flow control points at boundary points
Warp a timeseries
Warp an image
Perform decoder
Pad a list
Compute key - pad mask for key query
Prepare padded input
Get data for given split
Ensure folder exists
Builds the vocabulary
Adds results to json
Parse the hypothesis
Update the sum
Process a dictionary of sos and eos IDs
Recognize beam
Parse command line arguments
Calculate the CER function
Build LFR features
Forward the layer
Extract a feature
Extract data from a tar file

Get all kandi verified functions for this library.

Speech-Transformer Key Features

No Key Features are available at this moment for Speech-Transformer.

Speech-Transformer Examples and Code Snippets

Speech Transformer,Usage,Data Pre-processing

Python

Lines of Code : 14

License : Permissive (MIT)

Copy

$ python extract.py

$ cd data/data_aishell/wav
$ find . -name '*.tar.gz' -execdir tar -xzvf '{}' \;

$ python pre_process.py

Speech Transformer,Dataset

Python

Lines of Code : 8

License : Permissive (MIT)

Copy

@inproceedings{aishell_2017,
  title={AIShell-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline},
  author={Hui Bu, Jiayu Du, Xingyu Na, Bengu Wu, Hao Zheng},
  booktitle={Oriental COCOSDA 2017},
  pages={Submitted},
  year={

Speech Transformer,Usage,Train

Python

Lines of Code : 2

License : Permissive (MIT)

Copy

$ python train.py

$ tensorboard --logdir runs

Community Discussions

Trending Discussions on Speech-Transformer

What is attention penalty in speech transformer paper? (updated)

QUESTION

What is attention penalty in speech transformer paper? (updated)

Asked 2020-Jan-13 at 15:13

github: https://github.com/sephiroce/tfsr/tree/exprimental

I'm trying to reproduce recognition accuracies described in the speech transformer paper [1]. The attention penalty is a technique I could not fully understand. This is the description of the attention penalty in the paper.

"In addition, we encouraged the model attending to closer positions by adding bigger penalty on the attention weights of more distant position-pairs."

I understood as it means adding smaller negative values for more away from the diagonal on scaled attention logits (before masking) except for the first multi-head attention in decoders.

This is a code snippet for computing attention weights.

...

ANSWER

Answered 2020-Jan-13 at 10:33

I think you understand it well. They probably did a stripe around the diagonal, something like:

Source https://stackoverflow.com/questions/59646954

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install Speech-Transformer

You can download it from GitHub.
You can use Speech-Transformer like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: