### Install System Dependencies Source: https://github.com/nvidia/personaplex/blob/main/README.md Installs the required Opus audio codec development libraries on Linux-based systems. ```bash # Ubuntu/Debian sudo apt install libopus-dev # Fedora/RHEL sudo dnf install opus-devel ``` -------------------------------- ### Launch PersonaPlex Server Source: https://github.com/nvidia/personaplex/blob/main/README.md Starts the interactive server with SSL support. Includes an optional flag for CPU offloading when GPU memory is limited. ```bash # Standard launch SSL_DIR=$(mktemp -d); python -m moshi.server --ssl "$SSL_DIR" # Launch with CPU offload SSL_DIR=$(mktemp -d); python -m moshi.server --ssl "$SSL_DIR" --cpu-offload ``` -------------------------------- ### Install Python Dependencies Source: https://github.com/nvidia/personaplex/blob/main/README.md Installs the PersonaPlex package and optional CUDA-enabled PyTorch dependencies for Blackwell GPUs. ```bash pip install moshi/. pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu130 ``` -------------------------------- ### Perform Offline Evaluation Source: https://github.com/nvidia/personaplex/blob/main/README.md Runs the model in offline mode to process input audio files into output audio and text transcripts. Supports both assistant and service-oriented role prompts. ```bash # Assistant example HF_TOKEN= \ python -m moshi.offline \ --voice-prompt "NATF2.pt" \ --input-wav "assets/test/input_assistant.wav" \ --seed 42424242 \ --output-wav "output.wav" \ --output-text "output.json" # Service example HF_TOKEN= \ python -m moshi.offline \ --voice-prompt "NATM1.pt" \ --text-prompt "$(cat assets/test/prompt_service.txt)" \ --input-wav "assets/test/input_service.wav" \ --seed 42424242 \ --output-wav "output.wav" \ --output-text "output.json" ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.