five

Trelis/eval-whisper-small-multimed-hard-20260408-1933

收藏
Hugging Face2026-04-08 更新2026-04-12 收录
下载链接:
https://hf-mirror.com/datasets/Trelis/eval-whisper-small-multimed-hard-20260408-1933
下载链接
链接失效反馈
官方服务:
资源简介:
--- tags: - whisper - evaluation - speech - speech-to-text --- # Evaluation Results: whisper-small Evaluation results from Whisper model evaluation. ## Summary | Model | WER | CER | |-------|-----|-----| | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 13.31% | 7.49% | ## Source Data - **Evaluation Dataset:** [Trelis/multimed-hard](https://huggingface.co/datasets/Trelis/multimed-hard) - **Model Evaluated:** [openai/whisper-small](https://huggingface.co/openai/whisper-small) ## 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:** 22.85% | Category | CER | |----------|-----| | anatomy | 26.38% | | biomarker | 18.99% | | condition | 18.37% | | drug | 7.14% | | organisation | 32.67% | | procedure | 33.73% | --- *Generated by [Trelis Studio](https://studio.trelis.com)*

--- tags: - Whisper - 评估 - 语音 - 语音转文字 --- # 评估结果:Whisper-small 本内容为Whisper模型的评估结果。 ## 摘要 | 模型 | 词错误率(Word Error Rate, WER) | 字符错误率(Character Error Rate, CER) | |-------|-----|-----| | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 13.31% | 7.49% | ## 源数据 - **评估数据集:** [Trelis/multimed-hard](https://huggingface.co/datasets/Trelis/multimed-hard) - **本次评估的模型:** [openai/whisper-small](https://huggingface.co/openai/whisper-small) ## 字段说明 | 字段 | 描述 | |--------|-------------| | `audio` | 音频样本(若源数据集包含该数据) | | `reference` | 基准转录文本(真实标注) | | `prediction` | 模型预测转录结果 | | `wer` | 单样本词错误率 | | `cer` | 单样本字符错误率 | | `entities` | 源数据集自带的实体标注信息 | | `entity_cer` | 单样本实体字符错误率(无实体时取值为-1.0) | ## 实体字符错误率 **整体实体字符错误率:** 22.85% | 实体类别 | CER | |----------|-----| | 解剖学相关 | 26.38% | | 生物标志物 | 18.99% | | 病症 | 18.37% | | 药物 | 7.14% | | 组织机构 | 32.67% | | 诊疗操作 | 33.73% | --- *由 [Trelis Studio](https://studio.trelis.com) 生成*
提供机构:
Trelis
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作