# Python 3.10. Install torch/torchaudio for your CUDA first (Colab already has them), then:
#   pip install -r requirements.txt
# and clone CosyVoice (see README). Versions below are the ones the samples were rendered with
# (pins loosened where Colab's preinstalled versions also work).
torch>=2.3
torchaudio>=2.3
transformers==4.51.3
huggingface_hub>=0.23
numpy==1.26.4
soundfile>=0.12
librosa>=0.10
onnxruntime-gpu>=1.18
HyperPyYAML>=1.2.2
modelscope>=1.20
conformer==0.3.2
diffusers==0.29.0
lightning>=2.2.4
omegaconf>=2.3.0
hydra-core==1.3.2
inflect>=7.3
x-transformers>=2.11
openai-whisper>=20231117
einops>=0.8
# pyworld>=0.3.4   # CosyVoice training only; infer.py runs without it
pyarrow>=18
wget==3.2
gdown>=5.1
rich>=13.7
matplotlib>=3.7
protobuf>=4.25
pydantic>=2.7
wetext==0.0.4
audiotsm==0.1.2   # WSOLA time-stretch for --speed (falls back to librosa if missing)
gradio>=4.44,<6   # app.py
# optional, for --lid glotlid / the GlotLID checkbox:  fasttext (or fasttext-wheel)