Soohwan Kim

conformer. [Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

kospeech. Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.

attentions. PyTorch implementation of some attentions for Deep Learning Researchers.

k-startups. List of tech startups in South Korea. (2021)

Korean-PLM. List of Korean pre-trained language models.

ksponspeech. Pre-processing KsponSpeech corpus (Korean Speech dataset) provided by AI Hub.

pytorch-lr-scheduler. PyTorch implementation of some learning rate schedulers for deep learning researcher.

RNN-Transducer. PyTorch implementation of RNN-Transducer(RNN-T).

Speech-Recognition-Tutorial. 한국어 음성인식 튜토리얼

speech-transformer. Transformer implementation speciaized in speech recognition tasks using Pytorch.

nlp-tasks. Natural Language Processing Tasks and Examples.

lightning-asr. Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.

luna-transformer. A PyTorch Implementation of the Luna: Linear Unified Nested Attention

End-to-End-Speech-Recognition-Models. PyTorch implementation of automatic speech recognition models.

transformer. A PyTorch Implementation of "Attention Is All You Need"

openspeech. Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

taKotron2. Tacotron2 for Korean (taKotron2)

jasper. PyTorch implementation of "Jasper: An End-to-End Convolutional Neural Acoustic Model" (INTERSPEECH 2019)

deepspeech2. PyTorch implementation of "Deep Speech 2: End-to-End Speech Recognition in English and Mandarin" (ICML, 2016)

seq2seq. PyTorch implementation of the RNN-based sequence-to-sequence architecture.

speech-recognition-papers. Awesome Automatic Speech Recognition (ASR) paper collection

Naver-AI-Hackathon-Speech. 2019 Clova AI Hackathon : Speech - Rank 12 / Team Kai.Lib

tacotron2. Pytorch implementation of "Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions", ICASSP, 2018.

speech-paper-review. Review of papers I read

char-rnnlm. Character-level Recurrent Neural Network Language Model (rnnlm) implement in Pytorch.

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

sooftware.

Audio-Signal-Processing. Audio Signal Preocessing: pcm2wav, wav2pcm, feature extraction, augment, delete silence etc

accelerate-asr. Modular and extensible speech recognition library leveraging accelerate and hydra.

our-wedding-invitation. 직접 만든 모바일 청첩장 (w/ AI Chatbot) · Mobile wedding invitation with AI chatbot

Speech-Note. :headphones: Speech study records repository

generate-sec-dataset. Generate space error correction dataset

TIL. Today I Learned

gpticon. Upload your selfie, pick a vibe, and get AI-generated emoticons. GPT does the drawing, you do the flexing. 🐣✨

KoSpeech-Flask. KoSpeech Flask Web Application

metacode-202510. Jupyter Notebook

sooftware.io. My personal blog powered by react (gatsby)

datasets. 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

optimum. 🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools