Trelis/eval-parakeet-tdt-0.6b-v3-medical-terms-2025-20260408-1926
收藏资源简介:
--- tags: - whisper - evaluation - speech - speech-to-text --- # Evaluation Results: parakeet-tdt-0.6b-v3 Evaluation results from Whisper model evaluation. ## Summary | Model | WER | CER | |-------|-----|-----| | [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) | 11.34% | 3.63% | ## Source Data - **Evaluation Dataset:** [Trelis/medical-terms-2025](https://huggingface.co/datasets/Trelis/medical-terms-2025) - **Model Evaluated:** [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) ## Columns | Column | Description | |--------|-------------| | `audio` | Audio sample (if available from source dataset) | | `reference` | Ground truth transcription | | `prediction` | Model prediction | | `wer` | Word Error Rate for this sample | | `cer` | Character Error Rate for this sample | | `entities` | Entity annotations from source dataset | | `entity_cer` | Per-sample entity CER (-1.0 if no entities) | ## Entity CER **Overall Entity CER:** 24.62% | Category | CER | |----------|-----| | biomarker | 4.17% | | condition | 13.11% | | drug | 27.48% | | procedure | 6.45% | --- *Generated by [Trelis Studio](https://studio.trelis.com)*
标签: - Whisper(语音识别模型) - 模型评估 - 语音 - 语音转文字 --- # 评估结果:parakeet-tdt-0.6b-v3 本结果源自Whisper(语音识别模型)的评估测试。 ## 摘要 | 模型 | 词错误率(WER) | 字符错误率(CER) | |-------|-----|-----| | [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) | 11.34% | 3.63% | ## 源数据集信息 - **评估数据集:** [Trelis/medical-terms-2025](https://huggingface.co/datasets/Trelis/medical-terms-2025) - **待评估模型:** [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) ## 列说明 | 列名 | 描述 | |--------|-------------| | `audio` | 音频样本(若源数据集提供) | | `reference` | 基准转录文本(真实标注) | | `prediction` | 模型预测转录结果 | | `wer` | 该样本的词错误率(Word Error Rate, WER) | | `cer` | 该样本的字符错误率(Character Error Rate, CER) | | `entities` | 源数据集自带的实体标注 | | `entity_cer` | 单样本实体字符错误率(若无实体则标注为-1.0) | ## 实体字符错误率 **整体实体字符错误率:** 24.62% | 类别 | CER | |----------|-----| | 生物标志物 | 4.17% | | 病症 | 13.11% | | 药物 | 27.48% | | 诊疗操作 | 6.45% | --- *由 [Trelis Studio](https://studio.trelis.com) 生成*



