VoiceSpeechMaker-core-Demo / requirements.txt
WariHima's picture
transformerバージョンを固定
15afc70
raw
history blame contribute delete
632 Bytes
# accelerate
aivmlib
#cmudict
#cn2an
fastapi[standard]
e2k
# faster-whisper==0.10.1
g2p_en
# GPUtil
# gradio>=4.32
jaconv
jieba
# librosa==0.9.2
loguru
nltk<=3.8.1
num2words
numpy<2
onnx
onnxconverter-common
onnxruntime; (sys_platform != 'linux' or platform_machine != 'x86_64') and sys_platform != 'win32'
onnxruntime-directml; sys_platform == 'win32'
onnxruntime-gpu; sys_platform == 'linux' and platform_machine == 'x86_64'
onnxsim
# protobuf==4.25
psutil
# punctuators
pyannote.audio>=3.1.0
# pyloudnorm
pyopenjtalk-mod
pypinyin
pyworld-prebuilt
# stable_ts
# tensorboard
torch
torchaudio
transformers==4.48
umap-learn
zstandard