69 lines
1002 B
Plaintext
69 lines
1002 B
Plaintext
#git+https://github.com/facebookresearch/audiocraft.git
|
|
google-api-python-client
|
|
google-auth-oauthlib
|
|
google-auth-httplib2
|
|
oauth2client
|
|
httplib2
|
|
GitPython
|
|
librosa
|
|
moviepy
|
|
openai-whisper
|
|
addict
|
|
diffusers
|
|
ffmpeg-python
|
|
imageio-ffmpeg
|
|
|
|
# core deps for xtts
|
|
numpy==1.22.0;python_version<="3.10"
|
|
numpy>=1.24.3;python_version>"3.10"
|
|
cython>=0.29.30
|
|
scipy>=1.11.2
|
|
#torch>=2.1
|
|
torchaudio
|
|
soundfile>=0.12.0
|
|
librosa>=0.10.0
|
|
scikit-learn>=1.3.0
|
|
numba>=0.57.0;python_version>="3.9"
|
|
inflect>=5.6.0
|
|
tqdm>=4.64.1
|
|
anyascii>=0.3.0
|
|
pyyaml>=6.0
|
|
fsspec>=2023.6.0 # <= 2023.9.1 makes aux tests fail
|
|
aiohttp>=3.8.1
|
|
packaging>=23.1
|
|
mutagen==1.47.0
|
|
|
|
|
|
# deps for inference
|
|
pysbd>=0.3.4
|
|
|
|
# deps for training
|
|
matplotlib>=3.7.0
|
|
|
|
# coqui stack
|
|
# trainer
|
|
|
|
# config management
|
|
coqpit>=0.0.16
|
|
|
|
|
|
#deps for tortoise
|
|
einops>=0.6.0
|
|
transformers>=4.33.0
|
|
#deps for bark
|
|
encodec>=0.1.1
|
|
|
|
# deps for XTTS
|
|
unidecode>=1.3.2
|
|
num2words
|
|
# spacy[ja]>=3
|
|
#TTS
|
|
coqui-tts[languages] == 0.24.2
|
|
|
|
#deps for ocr
|
|
pytesseract
|
|
scikit-image
|
|
h5py
|
|
|
|
opencv-python
|