keonlee9420/Comprehensive-Tacotron2
PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.
PythonMIT
Issues
- 1
about train error
#10 opened by yyh565655555 - 1
preprocess.py error
#8 opened by boboaidalishi - 1
not find "speakers.json"
#9 opened by boboaidalishi - 1
Can't install or run
#7 opened by chrisbward - 0
how to train chinese
#6 opened by xiao-song2022 - 2
About package numba
#5 opened by ThanhPham1987 - 8
About hifigan package
#4 opened by ThanhPham1987 - 2
What GPU did you use to train the models?
#2 opened by d3on4pcsm - 5
some questions about synthesize
#3 opened by guoaoo - 3
Broken link to pretrained models
#1 opened by mbarnig