qute012 / kosr
Korean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)
☆30Updated 3 years ago
Related projects: ⓘ
- End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.☆10Updated 2 years ago
- 음성인식과 신호처리☆14Updated 3 years ago
- ☆9Updated last month
- Convert Numerical Representations to Korean Pronunciation☆14Updated 4 years ago
- Paper Review about Speech Recognition · NLP☆9Updated 3 years ago
- ☆36Updated 3 years ago
- ☆82Updated last year
- Pre-processing KsponSpeech corpus (Korean Speech dataset) provided by AI Hub.☆89Updated 2 years ago
- Korean text normalization and language preparation package for LM in Kaldi-based ASR system☆59Updated 4 years ago
- 발화자 지정 모듈☆18Updated 9 months ago
- Jasper 기반 양자화된 모델인 Quartznet 한국어 음성인식☆20Updated 3 years ago
- Korean Speech to English Translation Corpus☆39Updated 3 years ago
- ☆13Updated this week
- A Fairseq implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.☆11Updated 3 years ago
- ☆38Updated this week
- 2019 Clova AI Hackathon : Speech - Rank 12 / Team Kai.Lib☆23Updated 4 years ago
- Repository for speech paper reading☆32Updated 3 years ago
- Korean ASR Corpus generated from TEDx talks☆27Updated 5 years ago
- Pytorch implementation of "Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions", ICASSP, 2018.☆19Updated 3 years ago
- RNN-Transducer for korean☆38Updated 3 years ago
- 다양한 feature와 deep learning을 이용한 Phoneme Recognition입니다.☆13Updated 4 years ago
- ☆16Updated 9 months ago
- Review of papers I read☆14Updated 3 years ago
- ☆39Updated 4 years ago
- Prosody-semantics Interface in Seoul Korean☆12Updated 3 years ago
- Korean read speech corpus (about 120 hours, 17GB) from National Institute of Korean Language☆43Updated 6 years ago
- 5-class Korean speech emotion classifier☆30Updated last year
- Wav2Vec2 finetune and inference code for IITP AI Grand Challenge☆36Updated 2 years ago
- Multi-speaker & Multi-style TTS☆28Updated 2 months ago
- Use FastSpeech2 and HiFi-GAN to easily perform end-to-end Korean speech synthesis.☆27Updated last year