TTS-Talker / requirements.txt
Quang Long
update src/f5_tts, app.py, app_tts.py, add pyproject.toml
b8c51d6
torch==2.4.0
torchaudio==2.4.0
torchvision==0.19.0
face_alignment==1.3.0
imageio==2.19.3
imageio-ffmpeg==0.4.7
librosa==0.8.0
numba==0.56.4
resampy==0.3.1
pydub==0.25.1
scipy
kornia==0.6.8
tqdm
yacs==0.1.8
pyyaml
joblib==1.1.0
scikit-image==0.19.3
basicsr @ git+https://github.com/XPixelGroup/BasicSR.git@8d56e3a045f9fb3e1d8872f92ee4a4f07f886b0a
facexlib
dlib-bin
gfpgan
av
safetensors
gradio
soundfile
transformers
bitsandbytes>0.37.0
vinorm
cached_path
huggingface_hub
accelerate>=0.33.0
click
datasets
ema_pytorch>=0.5.2
hydra-core>=1.3.0
jieba
matplotlib
pypinyin
tomli
torchdiffeq
transformers_stream_generator
vocos
wandb
x_transformers>=1.31.14
# f5-tts
spaces
soxr
ffmpeg