ground-zero / .env.example
Broulaye Doumbia
Fix model loading stuck forever + unhandled TTS crash in conversation mode
618eab5
Raw
History Blame Contribute Delete
605 Bytes
# HuggingFace read token (required for accessing google/waxal dataset)
HF_TOKEN=hf_your_token_here
# Whisper model (used by app.py Gradio UI)
WHISPER_MODEL_ID=openai/whisper-large-v3-turbo
# LLM for conversation mode (HF Inference API)
LLM_MODEL_ID=Qwen/Qwen2.5-7B-Instruct
# Adapter paths (relative to project root)
BAMBARA_ADAPTER_PATH=./adapters/bambara
FULA_ADAPTER_PATH=./adapters/fula
# IoT sensor API endpoint (leave empty to use mock data in development)
SENSOR_API_URL=
# FastAPI server
API_HOST=0.0.0.0
API_PORT=8000
LOG_LEVEL=INFO
# Device: "cuda" for GPU, "cpu" for CPU-only
DEVICE=cuda