transformers==4.10.3 | |
datasets | |
huggingface-hub>=0.19 | |
hf-transfer>=0.1.4 | |
protobuf<4 | |
click<8.1 | |
pydantic~=1.0 | |
librosa==0.8.1 | |
torch==2.2.0 | |
torchaudio==2.2.0 | |
scipy | |
Cython==0.29.21 | |
phonemizer==2.2.1 | |
scikit-learn | |
matplotlib | |
gradio==3.1.4 | |
sentencepiece | |
sacremoses | |
tokenizers==0.10.3 | |
resampy>=0.2.2 | |
numba>=0.43.0 | |
soundfile>=0.10.2 | |
pooch>=1.0 | |
decorator>=3.0.0 | |
joblib>=0.14 | |
audioread>=2.0.0 | |