requirements.txt

gradio>=4.0.0
transformers>=4.30.0
torch>=2.0.0
torchaudio>=2.0.0
numpy>=1.21.0
soundfile>=0.12.0
pydub>=0.25.0
librosa>=0.10.0
datasets>=2.10.0 # For loading VCTK for speaker embeddings
accelerate>=0.20.0
speechbrain # Required for x-vector speaker embeddings