singing_voice_conversion / pre-requirements.txt
RMSnow's picture
try to fix fairseq installation bugs
c7b3d02
raw
history blame
480 Bytes
setuptools
ruamel.yaml
tqdm
colorama
easydict
tabulate
loguru
json5
Cython
unidecode
inflect
argparse
g2p_en
tgt
librosa
matplotlib
typeguard
einops
omegaconf
hydra-core
humanfriendly
pandas
tensorboard
tensorboardX
torch==2.0.1
torchaudio==2.0.2
torchvision==0.15.2
transformers
diffusers
accelerate
praat-parselmouth
audiomentations
pedalboard
ffmpeg-python==0.2.0
pyworld
diffsptk
nnAudio
unidecode
inflect
ptwt
torchmetrics
pymcd
openai-whisper
frechet_audio_distance
asteroid