蚂蚁集团 Ming-3.0-tts 以 0.5B 参数实现顶级语音合成质量
Ant Group's Ming-3.0-tts fits top-tier Text to Speech quality into just 0.5B parameters, and it is MIT licensed and punches well above its weights
蚂蚁集团发布 Ming-3.0-tts，以 0.5B 参数实现顶级文本转语音质量，并采用 MIT 许可。Artificial Analysis 称，它是其语音合成榜单前三中唯一参数量低于 1B 的模型；在 Controlled Voice Arena 前十中，其他开源权重 TTS 模型均为 3.5B 或更大，Ming-3.0-tts 以少 7 至 70 倍的参数达到同一档位。
正文
Ant Group's Ming-3.0-tts fits top-tier Text to Speech quality into just 0.5B parameters, and it is MIT licensed and punches well above its weights
It is the only model under 1B parameters in the top 3 of any of our Text to Speech leaderboards. Every other open weights TTS model in the top 10 of our Controlled Voice Arena is 3.5B or larger, so @AntLingAGI's Ming-3.0-tts reaches the same tier with 7x to 70x fewer parameters.
Links below 🧵