---
id: 20260325-T0-03
title: "Hugging Face推出语音助手评估框架EVA"
title_en: "Hugging Face Launches EVA Framework for Voice Agent Evaluation"
url: https://ai.daily.yangsir.net/daily/20260325-T0-03
issue_date: 2026-03-25
publish_date: 2026-03-24T02:01:52.000Z
category: tools
source_name: "Hugging Face Blog"
source_url: https://huggingface.co/blog/ServiceNow-AI/eva
---

# Hugging Face推出语音助手评估框架EVA

Hugging Face发布语音助手评估框架EVA（Evaluation of Voice Agents）。该框架提供标准化的评估指标，包括对话流畅度、任务完成准确率、响应延迟等关键维度。EVA支持多种语音模型对比测试，开发者可快速评估模型性能。目前支持英语评估，后续计划扩展多语言支持。框架已在GitHub开源，采用MIT许可证。

## English Version

**Hugging Face Launches EVA Framework for Voice Agent Evaluation**

Hugging Face has released EVA (Evaluation of Voice Agents), a standardized framework for assessing voice assistant performance. It provides metrics for fluency, task accuracy, and response latency. EVA supports comparative testing across multiple voice models and is currently English-focused, with multi-language support planned. The framework is open-sourced under MIT license on GitHub.

---

**来源**：[Hugging Face Blog](https://huggingface.co/blog/ServiceNow-AI/eva)

**详情页**：https://ai.daily.yangsir.net/daily/20260325-T0-03

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*