Soohwan Kim (@sooftware)
github

sooftware

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    2,571
  • Global Rank 11,712 (Top 0.5 %)
  • Followers 465
  • Following 71
  • Registered over 6 years ago
  • Most used languages
    Python
         92.3 %
    SCSS     3.8 %
    C
         3.8 %
  • Location 🇰🇷 South Korea
  • Country Total Rank 84
  • Country Ranking
    SCSS     30
    Python
         36
    C
         396

Top repositories

1

conformer

PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
Python
701
star
2

kospeech

Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
Python
600
star
3

attentions

PyTorch implementation of some attentions for Deep Learning Researchers.
Python
396
star
4

k-startups

List of tech startups in South Korea. (Republic of Korea)
206
star
5

Korean-PLM

List of Korean pre-trained language models.
157
star
6

ksponspeech

Pre-processing KsponSpeech corpus (Korean Speech dataset) provided by AI Hub.
Python
76
star
7

pytorch-lr-scheduler

PyTorch implementation of some learning rate schedulers for deep learning researcher.
Python
67
star
8

Speech-Recognition-Tutorial

한국어 음성인식 튜토리얼
60
star
9

nlp-tasks

Natural Language Processing Tasks and Examples.
Python
59
star
10

speech-transformer

Transformer implementation speciaized in speech recognition tasks using Pytorch.
Python
56
star
11

RNN-Transducer

PyTorch implementation of RNN-Transducer(RNN-T).
Python
51
star
12

lightning-asr

Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.
Python
42
star
13

End-to-End-Speech-Recognition-Models

PyTorch implementation of automatic speech recognition models.
Python
41
star
14

transformer

A PyTorch Implementation of "Attention Is All You Need"
Python
37
star
15

luna-transformer

A PyTorch Implementation of the Luna: Linear Unified Nested Attention
Python
35
star
16

jasper

PyTorch implementation of "Jasper: An End-to-End Convolutional Neural Acoustic Model" (INTERSPEECH 2019)
Python
29
star
17

Naver-AI-Hackathon-Speech

2019 Clova AI Hackathon : Speech - Rank 12 / Team Kai.Lib
Python
23
star
18

deepspeech2

PyTorch implementation of "Deep Speech 2: End-to-End Speech Recognition in English and Mandarin" (ICML, 2016)
Python
19
star
19

seq2seq

PyTorch implementation of the RNN-based sequence-to-sequence architecture.
Python
19
star
20

tacotron2

Pytorch implementation of "Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions", ICASSP, 2018.
Python
17
star
21

speech-paper-review

Review of papers I read
15
star
22

speech-recognition-papers

Awesome Automatic Speech Recognition (ASR) paper collection
15
star
23

Fairseq-Listen-Attend-Spell

A Fairseq implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.
Python
14
star
24

char-rnnlm

Character-level Recurrent Neural Network Language Model (rnnlm) implement in Pytorch.
Python
12
star
25

accelerate-asr

Modular and extensible speech recognition library leveraging accelerate and hydra.
Python
10
star
26

sooftware

10
star
27

Speech-Note

🎧 Speech study records repository
C
7
star
28

Audio-Signal-Processing

Audio Signal Preocessing: pcm2wav, wav2pcm, feature extraction, augment, delete silence etc
Python
7
star
29

generate-sec-dataset

Generate space error correction dataset
Python
6
star
30

TIL

Today I Learned
Python
6
star
31

sooftware.github.io

SCSS
6
star
32

KoSpeech-Flask

KoSpeech Flask Web Application
Python
3
star