What problem does it solve? Evaluating speech understanding models on Ascend NPU hardware 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 metrics. ## Core Features & Use Cases - Automated Container Orchestration: Launches a preconfigured Docker container with Ascend NPU device passthrough, driver mounts, and volume mappings for models, datasets, and configs. - Inference Execution & Metric Collection: Runs infer_runner.py against the foundation-lid LMDB dataset and extracts ACC (accuracy), avg_inference_time, success_rate, and total_samples into a structured result.json. - Use Case: An engineer needs to verify that the ECAPA-TDNN language identification model meets accuracy targets on Ascend 910B before deployment. The Skill guides container startup, runs inference over 1000 foundation-lid samples, and reports ACC plus per-sample inference time. ## Quick Start Ask the agent to test the lang-id-voxlingua107-ecapa language identification model inference performance on Ascend NPU with the foundation-lid dataset.
