Donghwa-KIM / audiotext-transformerLinks
cross-modal model between audio(MFCC) and text(KoBERT)
☆12Updated 4 years ago
Alternatives and similar repositories for audiotext-transformer
Users that are interested in audiotext-transformer are comparing it to the libraries listed below
Sorting:
- ☆87Updated 2 years ago
- ☆37Updated 4 years ago
- Multimodal Transformer for Korean Sentiment Analysis with Audio and Text Features☆28Updated 3 years ago
- A short tutorial on Keras for the co-utilization of audio and text data (multi-modal analysis)☆16Updated 2 years ago
- 오디오 전처리 작업을 위한 연습☆25Updated 6 years ago
- Pre-processing KsponSpeech corpus (Korean Speech dataset) provided by AI Hub.☆93Updated 3 years ago
- 발화자 지정 모듈☆21Updated 6 months ago
- ClovaCall dataset and Pytorch LAS baseline code (Interspeech 2020)☆222Updated 3 years ago
- Review of papers I read☆14Updated 4 years ago
- PyTorch implementation of "Jasper: An End-to-End Convolutional Neural Acoustic Model" (INTERSPEECH 2019)☆32Updated 4 years ago
- RNN-Transducer for korean☆43Updated 4 years ago
- Repository for speech paper reading☆33Updated 4 years ago
- ☆39Updated 5 years ago
- ☆99Updated 2 years ago
- 한국어 음성인식 튜토리얼☆64Updated 5 years ago
- Korean grapheme-to-phone conversion in Python☆133Updated 5 years ago
- Wav2Vec2 finetune and inference code for IITP AI Grand Challenge☆36Updated 3 years ago
- Korean Speech to English Translation Corpus☆44Updated 4 years ago
- Korean text normalization and language preparation package for LM in Kaldi-based ASR system☆62Updated 5 years ago
- 2019 Clova AI Hackathon : Speech - Rank 12 / Team Kai.Lib☆22Updated 5 years ago
- Transformer implementation speciaized in speech recognition tasks using Pytorch.☆64Updated 3 years ago
- PyTorch v1.2에서 생긴 Transformer API 를 이용한 간단한 Chitchat 챗봇☆48Updated 6 years ago
- Korean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)☆30Updated 4 years ago
- A PyTorch Implementation of "Attention Is All You Need"☆38Updated 3 years ago
- ☆18Updated 4 years ago
- Various Text-to-speech (TTS) papers based on Deep-learning☆14Updated 4 years ago
- g2pK: g2p module for Korean☆257Updated 3 years ago
- A Fairseq implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.☆11Updated 4 years ago
- Multi-speaker & Multi-style TTS☆29Updated last year
- This is project to analyze korquad 2.0☆24Updated 3 years ago