What problem does it solve? Evaluating speech understanding models on NVIDIA GPUs requires manual container setup, dataset mounting, inference execution, and metric collection. This Skill automates the full evaluation workflow for the lang-id-voxlingua107-ecapa language identification model, producing standardized ACC and latency reports. ## Core Features & Use Cases - Automated Container Orchestration: Launches a prebuilt Docker evaluation environment with correct GPU, shared memory, and volume mount configurations. - Standardized Inference Evaluation: Runs the infer_runner.py pipeline against the foundation-lid LMDB dataset and collects predictions and logs. - Metric Extraction: Parses acc_report.json to produce ACC (accuracy), avg_inference_time, success_rate, and total_samples in a structured result.json. - Use Case: An engineer needs to verify that the VoxLingua107 ECAPA-TDNN model meets accuracy targets on an NVIDIA H200. The Skill starts the container, runs inference on 1000 samples, and outputs a JSON report with accuracy and per-sample inference time. ## Quick Start Ask the agent to test the lang-id-voxlingua107-ecapa language identification model inference performance on NVIDIA GPU with the foundation-lid dataset.
