kaituoxu/ Listen-Attend-Spell

Python

Shell

asr

end-to-end

pytorch

View on GitHub

Need help with Listen-Attend-Spell?

Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

kaituoxu

145 Stars

48 Forks

24 Commits

9 Opened issues

Description

A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.

Services available

Need anything else?

Contributors list

Kaituo XU 许开拓 kaituoxu

# 49,771

Python

Shell

pytorch

self-at...

24 commits

Readme

Listen, Attend and Spell

Name: Listen-Attend-Spell
Brand: Listen-Attend-Spell
SKU: //kaituoxu/Listen-Attend-Spell
Rating: 2.1125 (145 reviews)

A PyTorch implementation of Listen, Attend and Spell (LAS) [1], an end-to-end automatic speech recognition framework, which directly converts acoustic features to character sequence using only one nueral network.

Install

Python3 (Recommend Anaconda)
PyTorch 0.4.1+
Kaldi (Just for feature extraction)
```
pip install -r requirements.txt
```
```
cd tools; make KALDI=/path/to/kaldi
```
If you want to run
```
egs/aishell/run.sh
```
, download aishell dataset for free.

Usage

```
$ cd egs/aishell
```
and modify aishell data path to your path in
```
run.sh
```
.
```
$ bash run.sh
```
, that's all!

You can change hyper-parameter by

$ bash run.sh --parameter_name parameter_value

, egs,

$ bash run.sh --stage 3

. See parameter name in

egs/aishell/run.sh

before

. utils/parse_options.sh

More detail

$ cd egs/aishell/
$ . ./path.sh

Train

bash
$ train.py -h

Decode

bash
$ recognize.py -h

Workflow

Workflow of

egs/aishell/run.sh

: - Stage 0: Data Preparation - Stage 1: Feature Generation - Stage 2: Dictionary and Json Data Preparation - Stage 3: Network Training - Stage 4: Decoding

Visualize loss

If you want to visualize your loss, you can use

visdom

to do that: - Open a new terminal in your remote server (recommend tmux) and run

$ visdom

. - Open a new terminal and run

$ bash run.sh --visdom 1 --visdom_id ""

$ train.py ... --visdom 1 --vidsdom_id ""

. - Open your browser and type

:8097

, egs,

127.0.0.1:8097

. - In visdom website, chose

Environment

to see your loss.

Results

| Model | CER | Config | | :---: | :-: | :----: | | LSTMP | 9.85| 4x(1024-512) | | Listen, Attend and Spell | 13.2 | See egs/aishell/run.sh |

Reference

[1] W. Chan, N. Jaitly, Q. Le, and O. Vinyals, “Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,” in ICASSP 2016. (https://arxiv.org/abs/1508.01211v2)