text_to_speech_sync_video / requirements.txt
zmbfeng's picture
correct typo in numpy version
a0e95c2
raw
history blame
238 Bytes
librosa==0.8.0
transformers==4.22.2
ffmpeg-python
SpeechRecognition
pydub
gTTS
numpy==1.23.5
opencv-contrib-python
opencv-python
torchvision
tqdm
numba
basicsr>=1.4.2
facexlib>=0.2.5
lmdb
pyyaml
scipy
tb-nightly
torch>=1.7
yapf
realesrgan