AI-Speech-Translator / requirements.txt
SidML's picture
Initial Upload
5a65ad6 verified
raw
history blame contribute delete
722 Bytes
# Core dependencies for Speech Translation System with Voice Cloning (Python 3.13 compatible)
torch>=2.0.0
torchaudio>=2.0.0
transformers>=4.30.0
# Speech Recognition
openai-whisper
librosa>=0.10.0
soundfile>=0.12.1
# Translation
# googletrans==4.0.0rc1 # Commented due to dependency conflicts
requests>=2.28.0
# Text-to-Speech
pyttsx3>=2.90
gTTS>=2.3.0
pygame>=2.1.0
# Audio Processing
pydub>=0.25.1
scipy>=1.10.0
numpy>=1.24.0
matplotlib>=3.7.0
# Web Interface and API
gradio>=5.44.0
fastapi>=0.100.0
uvicorn>=0.22.0
# Utilities
python-dotenv>=1.0.0
click>=8.1.0
tqdm>=4.65.0
rich>=13.4.0
pyyaml>=6.0
psutil>=5.9.0
# Development and Testing
pytest>=7.4.0
pytest-cov>=4.1.0