
Open TTS Leaderboard:多语种TTS评测
用客观指标扩展评测开源多语种TTS和声音克隆模型。
为什么重要
为开源TTS模型提供更快、更标准化的可懂度、速度和相似度评估。
阅读原文huggingface.co
AI 解读(根据原文生成)
Hugging Face Blog 介绍了 Open TTS Leaderboard,面向开源和多语种文本转语音模型的可扩展评测。该榜单用客观指标评估互补能力:借助 Qwen3 ASR 计算生成音频转写与提示文本之间的 WER/CER 衡量可懂度;在 H200 GPU 和 CPU 上测量 RTFx 与 TTFA 衡量速度;用 WavLM 说话人嵌入余弦相似度衡量声音相似度。文章强调它不替代人工偏好排名,但可帮助快速筛选待评测模型。
要点(AI 据原文整理,数字均已与原文核对)
- On the Hugging Face Hub (as of Sep 30, 2026) there are more than 8K TTS models available.
- As of Sep 30, 2026, only 16 of the 92 models on Artificial Analysis are open-weights.
- Speaker similarity is computed as cosine similarity between WavLM speaker embeddings of generated audio and the reference clip.
- By relying on objective metrics evaluating a model drops from a couple weeks to a couple hours.