Issues
- 0
Memory leak issue
#148 opened by gbaian10 - 1
Should support for python3.9 be dropped?
#145 opened by gbaian10 - 0
version 0.4.7 by misaki, works wrong.
#147 opened by zhongtanru - 4
It can't be packed by version 0.4.7
#143 opened by zhongtanru - 0
- 2
Package miss `py.typed` file
#142 opened by gbaian10 - 2
Multiple `voices_path` inputs
#141 opened by gbaian10 - 7
Need native speakers to verify
#137 opened by thewh1teagle - 7
Issues Encountered When Generating Chinese Audio
#114 opened by JV-X - 1
- 0
How can I help to add Greek?
#139 opened by RoseSamaras - 4
UnicodeDecodeError: 'charmap' codec can't decode byte... on import with v0.4.6 on Windows
#138 opened by drgutman - 25
Kokoro-82M-v1.1-zh
#127 opened by shadowcz007 - 5
[Chinese language] Can it support more other languages such as Chinese?
#118 opened by GreatDongsong - 7
The pronunciation of Chinese is a bit touching
#119 opened by Nicolas-XF - 2
Help needed: MacOS requires onnxruntime>=1.20.1
#126 opened by redo33 - 7
It's not clear whether it's a problem with the code, but the Chinese audio I generated here is really terrible
#131 opened by Nicolas-XF - 4
- 10
How to use GPU, the default is the CPU used
#92 opened by Nicolas-XF - 7
Some Chinese text pronunciations are weird.
#101 opened by lyris - 1
Invalid link in the README
#128 opened by alonsosilvaallende - 3
- 3
First call slow on macOS
#100 opened by thewh1teagle - 2
- 3
Does it support LINUX on ARM64 architecture?
#134 opened by mixiuemo - 2
- 3
Index out of bounds in _create_audio()
#115 opened by maxpatiiuk - 0
Can't install nvidia-nccl-cu12 and triton
#129 opened by zhongtanru - 6
- 1
How to support mixed languages, such as English words in a Japanese sentence?
#122 opened by lokizero00 - 1
How to support mixed languages, such as English words in a Japanese sentence?
#123 opened by lokizero00 - 1
Consider bringing librosa trim functionality in-tree
#121 opened by evq - 5
Allow use with system espeak-ng and vanilla phonemizer
#120 opened by evq - 3
Can't run model on GPU
#117 opened by tanaka-mambinge - 0
return timestamps for words
#116 opened by thewh1teagle - 1
Model's performance on GPU is slow
#112 opened by lhr-30 - 1
- 1
JSON format question
#110 opened by DrChilla - 1
GPU CUDA encountered error: type object 'EspeakWrapper' has no attribute 'set_data_path'
#111 opened by muduolin - 4
- 11
Improve phonemize for multi-language support
#108 opened by HDANILO - 2
- 11
utf-8' codec can't decode byte 0xff in position 18
#103 opened by ilanzuo - 0
Chinese results sounds not right
#106 opened by lucasjinreal - 1
Batch support
#102 opened by ccyrene - 1
- 6
Index out of bounds in _create_audio()
#95 opened by j-venerable - 1
- 1
error: np issue in colab
#90 opened by Naol-bm - 2
voices-v1.0.bin file name problem
#91 opened by smartdawg