tensorflow_end2end_speech_recognition - GitLite

KO | EN

gitlite — search

#python #ai #golang #go #machine-learning #deep-learning #docker #nodejs #java #windows #awesome #kubernetes #ios #open-source

tensorflow_end2end_speech_recognition

(★ 314)

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

File Explorer

Download Latest Version (.zip)

- - __init__.py
  - README.md
- - __init__.py
  - attention_seq2seq.py
  - bridge.py
  - joint_ctc_attention.py
  - ListenAttendandSpell.py
- - __init__.py
  - bn_blstm_ctc.py
  - ctc.py
  - multitask_ctc.py
  - student_ctc.py
- - __init__.py
  - load_encoder.py
- - __init__.py
  - base.py
  - char_rnnlm.py
  - word_rnnlm.py
- - __init__.py
  - initializer.py
- - __init__.py
  - data.py
  - install_sample.sh
  - phone61.txt
  - run_attention.sh
  - run_ctc.sh
  - run_joint_ctc_attention.sh
  - run_multitask_ctc.sh
  - test_attention.py
  - test_ctc.py
  - test_ctc_decoder.py
  - test_encoder.py
  - test_joint_ctc_attention.py
  - test_multitask_ctc.py
- __init__.py
- model_base.py
- README.md
- - __init__.py
  - attention.py
  - base.py
  - ctc.py
  - joint_ctc_attention.py
  - multitask_ctc.py
  - xe.py
- - __init__.py
  - edit_distance.py
- - __init__.py
- - __init__.py
  - learning_rate_controller.py
  - multi_gpu.py
  - plot.py
- __init__.py
- directory.py
- measure_time_func.py
- parallel.py
- parameter.py
- progressbar.py
.gitignore
LICENSE
README.md
requirements.txt

# Installation Guide

1. Get the code

git clone https://github.com/hirofumi0810/tensorflow_end2end_speech_recognition

Downloads the entire project code from GitHub to your computer.

cd tensorflow_end2end_speech_recognition

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

## TensorFlow Implementation of End-to-End Speech Recognition
### Requirements
- TensorFlow >= 1.3.0
- tqdm >= 4.14.0
- python-Levenshtein >= 0.12.0
- setproctitle >= 1.1.10
- seaborn >= 0.7.1

### Corpus
#### [TIMIT](https://catalog.ldc.upenn.edu/LDC93S1)
- Phone (39, 48, 61 phones)
- character

#### [LibriSpeech](http://www.openslr.org/12/)
- Phone (under implementation)
- Character
- Word

#### [CSJ (Corpus of Spontaneous Japanese)](http://pj.ninjal.ac.jp/corpus_center/csj/en/)
- Phone (under implementation)
- Japanese kana character (about 150 classes)
- Japanese kanji characters (about 3000 classes)

These corpuses will be added in the future.
- Switchboard
- WSJ
- [AMI](http://groups.inf.ed.ac.uk/ami/corpus/)

This repository does'nt include pre-processing and pre-processing is based on [this repo](https://github.com/hirofumi0810/asr_preprocessing).
If you want to do pre-processing, please look at this repo.

### Model
#### Encoder
- BLSTM
- LSTM
- BGRU
- GRU
- VGG-BLSTM
- VGG-LSTM
- Multi-task BLSTM
  - you can set another CTC layer to the aubitrary layer.
- Multi-task LSTM
- VGG

#### Connectionist Temporal Classification (CTC) [\[Graves+ 2006\]](http://dl.acm.org/citation.cfm?id=1143891)
- Greedy decoder
- Beam Search decoder
- Beam Search decoder w/ CharLM (under implementation)

##### Options
- Frame-stacking [\[Sak+ 2015\]](https://arxiv.org/abs/1507.06947)
- Multi-GPUs training (synchronous)
- Splicing
- Down sampling (under implementation)

#### Attention Mechanism
##### Decoder
- Greedy decoder
- Beam search decoder (under implementation)

##### Attention type
- Bahdanau's content-based attention
- Bahdanau's normed content-based attention (under implementation)
- location-based attention
- Hybrid attention
- Luong's dot attention
- Luong's scaled dot attention (under implementation)
- Luong's general attention
- Luong's concat attention
- Baidu's attention (under implementation)

###### Options
- Sharpning
- Temperature regularization in the softmax layer (Output posteriors)
- Joint CTC-Attention [\[Kim 2016\]](https://arxiv.org/abs/1609.06773.)
- Coverage (under implementation)

### Usage
Please refer to docs in each corpuse
- TIMIT
- LibriSpeech
- CSJ

### Lisense
MIT

### Contact
hiro.mhbc@gmail.com