Multi-voice-TTS-GPT-SoVITS / requirements.txt
Ailyth's picture
0330-125210-improve_ENG_inference
d8137a5
raw
history blame contribute delete
356 Bytes
numpy
scipy
librosa==0.9.2
numba==0.56.4
pytorch-lightning
gradio==4.19.1
ffmpeg-python
onnxruntime
tqdm
cn2an
pypinyin
pyopenjtalk
g2p_en
torchaudio
modelscope==1.10.0
sentencepiece
transformers
chardet
PyYAML
psutil
jieba_fast
jieba
LangSegment
soundfile
git+https://github.com/huggingface/transformers
torch
pyicu
morfessor
pycld2
polyglot
wordsegment