thuhcsi / Crystal
Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.
☆225Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for Crystal
- Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.☆253Updated 5 years ago
- A Demo of Mandarin/Chinese TTS frontend☆277Updated 2 years ago
- Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - P…☆187Updated 3 weeks ago
- A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset☆337Updated 2 years ago
- Kaldi-based goodness of pronunciation (GOP)☆147Updated 3 years ago
- The code for aishell-3 baseline acoustic model☆68Updated 3 years ago
- Tacotron2 + LPCNET for complete End-to-End TTS System☆93Updated last year
- DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)☆298Updated 4 years ago
- ☆69Updated 3 years ago
- Include Basis-MelGAN, MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.☆154Updated 3 years ago
- ☆74Updated 2 years ago
- Implementation of "Duration Informed Attention Network for Multimodal Synthesis" paper in PyTorch.☆183Updated 4 years ago
- Official PyTorch implementation of Speaker Conditional WaveRNN☆109Updated 2 years ago
- Deepmind's Tacotron-2 Tensorflow implementation☆162Updated 4 years ago
- Chinese Text Normalization and Dataset☆81Updated 2 years ago
- style token with tacotron2☆61Updated last year
- PPG-Based Voice Conversion☆329Updated 2 years ago
- chinese tts☆74Updated 3 years ago
- TTS model based on Transformer.☆57Updated 5 years ago
- Forked from NVIDIA/tacotron2 and merged with Rayhane-mamah/Tacotron-2☆81Updated 4 years ago
- g2pC: A Context-aware Grapheme-to-Phoneme Conversion module for Chinese☆239Updated 5 years ago
- Opencpop: A High-Quality Open Source Chinese Popular Song Database for Singing Voice Synthesis☆211Updated last year
- Efficient neural speech synthesis☆80Updated 3 years ago
- The official implementation of VAENAR-TTS, a VAE based non-autoregressive TTS model.☆144Updated 3 years ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆371Updated 5 months ago
- VAE Tacotron 2, an alternative of GST Tacotron☆88Updated last year
- ☆142Updated 4 years ago
- Mel cepstral distortion (MCD) computations in python.☆213Updated 7 years ago
- Forced alignment and Goodness of Pronunciation (GOP) with DNN support. Bases on Kaldi.☆221Updated 5 years ago