What problem does it solve? Running speech recognition model benchmarks on PPU accelerator hardware requires manual container setup, dataset mounting, inference execution, and metric collection. This Skill automates the full evaluation workflow for SenseVoice ASR models, producing standardized accuracy (CER/WER) and throughput reports. ## Core Features & Use Cases - Automated Container Orchestration: Launches a preconfigured Docker container with PPU device mounting, volume mapping for models, datasets, and configs. - Multi-Dataset ASR Evaluation: Supports 28 speech recognition datasets including Aishell-1, LibriSpeech, FLEURS, and KeSpeech across Chinese, English, Japanese, Korean, and Cantonese. - Standardized Metrics Collection: Generates acc_report.json with CER (character error rate), WER (word error rate), average inference time, and success rate. - Use Case: Test the SenseVoiceSmall model on the Aishell-1 Chinese dataset to measure character error rate and per-sample inference latency on a PPU card. ## Quick Start Ask the agent to test SenseVoiceSmall speech recognition inference performance on PPU using the Aishell-1 dataset and collect CER metrics.
