Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix "gpt (chinese)" incorrect SRT timestamp format #612

Merged
merged 1 commit into from
May 30, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions 2024/gpt/chinese/captions.srt
Original file line number Diff line number Diff line change
Expand Up @@ -67,15 +67,15 @@ Transformer 是一种特定类型的神经网络,一个机器学习模型,
所有那些在 2022 年风靡全球的工具,

18
00:00:59,360 --> 00:01:04,239.99999999999272
00:00:59,360 --> 00:01:04,239
如 DALL-E 和 MidJourney,能够将文本描述转化为图像,

19
00:01:04,239.99999999999272 --> 00:01:05,519.9999999999927
00:01:04,239 --> 00:01:05,519
都是基于 Transformer 的。

20
00:01:05,519.9999999999927 --> 00:01:06,830
00:01:05,519 --> 00:01:06,830
即使我无法让它完全理解

21
Expand Down Expand Up @@ -159,11 +159,11 @@ Transformer 是一种特定类型的神经网络,一个机器学习模型,
这次的预测需要基于所有新生成的文字,

41
00:02:08,190 --> 00:02:09,919.9999999999854
00:02:08,190 --> 00:02:09,919
包括刚刚添加的那部分。

42
00:02:09,919.9999999999854 --> 00:02:10,780
00:02:09,919 --> 00:02:10,780
我不知道你怎么看,

43
Expand Down Expand Up @@ -231,7 +231,7 @@ Transformer 是一种特定类型的神经网络,一个机器学习模型,
能看到它在选择每个新词时的底层概率分布。

59
00:03:03,921.484375 --> 00:03:06,320
00:03:03,921 --> 00:03:06,320
我们先从宏观角度看看

60
Expand Down Expand Up @@ -687,11 +687,11 @@ GPT-3 的早期演示就是这样的,
你要做的,就是找出一条最拟合这些数据的直线,

173
00:08:35,120 --> 00:08:37,460.0000000000582
00:08:35,120 --> 00:08:37,460
以此来预测将来的房价。

174
00:08:37,460.0000000000582 --> 00:08:40,400
00:08:37,460 --> 00:08:40,400
这条线由两个连续的参数,

175
Expand Down Expand Up @@ -1335,11 +1335,11 @@ GPT-3 模型仍具有独特的魅力,
当它们指向相反方向时,点积为负。

335
00:17:05,520 --> 00:17:06,589.9999999998836
00:17:05,520 --> 00:17:06,589
例如,

336
00:17:06,589.9999999998836 --> 00:17:09,230
00:17:06,589 --> 00:17:09,230
假设你在测试这个模型,

337
Expand Down