#6036 我生成视频时配音不会跟着原语速去进行适配和断句,就像现在这样,这个是翻译出来的文件00:00:00,320 --> 00:00:32,048他的铲子碰到了什么东西,硬邦邦的。他扒开泥土,发现它在闪闪发光。他把它挖出来,在手里感觉异常沉

182.89* Posted at: 13 hours ago

我生成视频时配音不会跟着原语速去进行适配和断句,就像现在这样,这个是翻译出来的文件
00:00:00,320 --> 00:00:32,048
他的铲子碰到了什么东西,硬邦邦的。他扒开泥土,发现它在闪闪发光。他把它挖出来,在手里感觉异常沉重。他注意到侧面有一道裂缝,里面有光透出,一碰,就把手指割破了。那东西底部似乎可以转动,可他转动时,中心却升了起来,一按,伤口就消失了。他不明白,又试了一次。每按一次,世界就倒流。他开始恐慌起来。

他会在视频一开始就一口气念完这段,导致语言位置不和原语言位置匹配,帮我分析一下,下面是识别出来的原英文字幕
00:00:00,320 --> 00:00:58,100
His shovel struck something solid. As he pried away the dirt, he could see it shining. When he plucked it loose, it felt strangely heavy in his hand. He noticed that there was a crack on the side, with light coming out of it, and when he touched it, it sliced his finger clean. It looked like the bottom was meant to turn, but as he twisted it, the center lifted out, and when he pressed it, his cut was gone. He didn't understand, so he tried it again. The world was rewinding with each press. He started to panic.

1 Replies

这是翻译后的中文字幕被合并成了一条长字幕(原英文字幕正常分段)导致的。配音时会将这条长字幕视为一个连续段落,一口气读完,从而失去与原视频时间轴的匹配。

解决方法

  1. 重新执行翻译,在软件主界面勾选 「发送完整字幕」(位于翻译渠道下方),这会让 AI 保持原有字幕的行数和时间轴,避免合并。
  2. 若仍无效,请将 翻译渠道改为传统翻译(如 Google 或 Microsoft 翻译),这些渠道不会自动合并字幕。
  3. 确保 未勾选「合并过短字幕到相邻」(在菜单→工具→高级选项→语音识别参数里)。

这样处理后,翻译后的中文字幕会保持与原英文字幕相同的分段,配音就能逐句对位。

Post Your Reply
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Dondate via PayPal

Related resource