Main focus: Psycholinguistics / Mechine learning / Deep learning
NaturalSpeech2. Jupyter Notebook
139HiFiSinger. Python
111HierSpeech. Python
67Glow_TTS. An implement of GlowTTS model. Several modes are added: speaker embedding, prosody encoder(GST), and gradient reversal.
55multi_speaker_tts. Implementation of Multi speaker TTS
50AutoVC. Python
30GST_Tacotron. Implementation of Global Style Token Tacotron in TensorFlow2
26VITS_Diffusion. Python
26DiffSingerKR. Python
25MLPSinger. Jupyter Notebook
24XiaoiceSing2. Jupyter Notebook
19Speaker_Embedding_Torch. PyTorch based speaker embedding model
16SPEECHSPLIT. An implement of SPEECHSPLIT
15PWGAN_for_HiFiSinger. Python
11speaker_embedding. Python
9DiffWave. Jupyter Notebook
8GradTTS. Python
6WaveNet. A TF2 implementation of WaveNet
6Tisk. Python
5HNet_on_Tensorflow. HNet on Tensorflow. The PyQT is used for the GUI. Core file is Apache License 2.0. And GUI is GPL 3.0
5HierSpeechpp. Python
4XSinger. Python
3RHRNet. RHRNet unofficial code.
3PWGAN_Torch. Python
2WaveRNN. WaveRNN implementation
2HJ-Net. This program is for the GUI interface connectionist modeling.
2TacoSinger. Python
2Light_SERNet. Python
1stargan. StarGAN implementation
1listen_attend_spell. An implementation of LAS(Listen, Attend, and Spell) model
1PVCGAN_Torch. Python
1