VALL-E-X / requirements.txt
Plachta's picture
Replaced Encodec with Vocos
a5ba843
raw
history blame
242 Bytes
soundfile
numpy
torch==2.0.1
torchvision==0.15.2
torchaudio
tokenizers
encodec
vocos
langid
unidecode
pyopenjtalk
pypinyin
inflect
cn2an
jieba
eng_to_ipa
jieba
SudachiPy
sudachidict_core
nltk
openai-whisper
phonemizer
matplotlib
psutil
gradio