scarletcho / KoG2P
Korean grapheme-to-phone conversion in Python
☆127Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for KoG2P
- g2pK: g2p module for Korean☆236Updated 2 years ago
- Korean text normalization and language preparation package for LM in Kaldi-based ASR system☆59Updated 4 years ago
- Pre-processing KsponSpeech corpus (Korean Speech dataset) provided by AI Hub.☆89Updated 2 years ago
- RNN-Transducer for korean☆39Updated 4 years ago
- ☆36Updated 3 years ago
- TTS for pitch-accented language. Korean dialect DB.☆157Updated last year
- 오디오 전처리 작업을 위한 연습☆25Updated 5 years ago
- 음성합성 관련 자료 모음☆124Updated 6 years ago
- Korean read speech corpus (about 120 hours, 17GB) from National Institute of Korean Language☆43Updated 6 years ago
- ClovaCall dataset and Pytorch LAS baseline code (Interspeech 2020)☆218Updated 2 years ago
- ☆82Updated last year
- ☆70Updated 3 years ago
- Implementation of Korean FastSpeech2☆213Updated last year
- ☆39Updated 5 years ago
- Jejueo Datasets for Machine Translation and Speech Synthesis☆76Updated 4 years ago
- Tacotron, Korean, Wavenet-Vocoder, Korean TTS☆172Updated last year
- Korean TTS, Tacotron2, Wavenet☆165Updated 4 years ago
- A Fairseq implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.☆11Updated 3 years ago
- 한국어 음성인식 튜토리얼☆64Updated 4 years ago
- 로봇의 감정 및 개성을 표현할 수 있는 대화형 음성합성 오픈소스 플랫폼☆105Updated 3 years ago
- Adversarially Trained End-to-end Korean SInging Voice Synthesis System☆54Updated 4 years ago
- ☆92Updated last year
- Repository for speech paper reading☆32Updated 3 years ago
- Tacotron2 for Korean (taKotron2)☆34Updated 2 years ago
- Multi-speaker Tacotron in TensorFlow. 오픈소스 딥러닝 다중 화자 음성 합성 엔진.☆170Updated last year
- Grapheme-to-Phoneme(G2P) 관련자료 모음☆20Updated 6 years ago
- Korean TTS using coqui TTS (glowtts and multiband melgan) - 한국어 TTS☆53Updated 2 years ago
- STT 한글 문장 인식기 출력 스크립트의 외자 오류율(CER), 단어 오류율(WER)을 계산하는 Python 함수 패키지☆58Updated last year
- Use FastSpeech2 and HiFi-GAN to easily perform end-to-end Korean speech synthesis.☆27Updated last year