docs(zh-cn): Reviewed 04_the-transformer-architecture.srt

subtitles/zh-CN/04_the-transformer-architecture.srt

@@ -1,21 +1,21 @@
 1
 00:00:00,000 --> 00:00:02,750
-（徽标呼啸而过）
+（logo 闪过）
 (logo whooshing)
 
 2
 00:00:05,010 --> 00:00:07,323
-- 让我们 Transformer 的架构。
+- 今天我们来学习 Transformer 的架构。
 - Let's study the transformer architecture.
 
 3
 00:00:09,150 --> 00:00:12,030
-该视频是编码器的介绍视频，
+本视频是介绍编码器、解码器
 This video is the introductory video to the encoders,
 
 4
 00:00:12,030 --> 00:00:15,510
-解码器和编码器 - 解码器系列视频。
+编器-解码器的系列视频。
 decoders, and encoder-decoder series of videos.
 
 5
@@ -25,12 +25,12 @@ In this series,
 
 6
 00:00:16,343 --> 00:00:18,900
-我们将尝试了解是什么构成了 transformer 网络，
+我们将尝试了解 transformer 网络是怎么构成的，
 we'll try to understand what makes a transformer network,
 
 7
 00:00:18,900 --> 00:00:22,770
-我们将尝试用简单、高层次的术语来解释它。
+我们将尝试用简单、高层次的术语来进行解释。
 and we'll try to explain it in simple, high-level terms.
 
 8
@@ -40,12 +40,12 @@ No advanced understanding of neural networks is necessary,
 
 9
 00:00:25,800 --> 00:00:29,343
-但了解基本向量和张量可能会有所帮助。
+但关于基本向量和张量的知识可能会有所帮助。
 but an understanding of basic vectors and tensors may help.
 
 10
 00:00:32,250 --> 00:00:33,270
-开始，
+让我们开始吧，
 To get started,
 
 11
@@ -55,13 +55,13 @@ we'll take up this diagram
 
 12
 00:00:34,530 --> 00:00:36,630
-从原来的变压器纸，
+它来自 Vaswani 等人发表的原始 transformer 论文
 from the original transformer paper,
 
 13
 00:00:36,630 --> 00:00:40,140
-Vaswani 等人题为 “注意力就是你所需要的”。
-entitled "Attention Is All You Need", by Vaswani et al.
+题为 “注意力就是您所需要的（Attention Is All You Need）”。
+entitled "", by Vaswani et al.
 
 14
 00:00:40,140 --> 00:00:41,010
@@ -70,12 +70,12 @@ As we'll see here,
 
 15
 00:00:41,010 --> 00:00:42,780
-我们只能利用它的一部分，
+根据我们正在尝试做的事情
 we can leverage only some parts of it,
 
 16
 00:00:42,780 --> 00:00:44,630
-根据我们正在尝试做的事情。
+我们只能利用它的一部分。
 according to what we're trying to do.
 
 17
@@ -85,17 +85,17 @@ We want to dive into the specific layers,
 
 18
 00:00:47,610 --> 00:00:48,990
-建立那个架构，
+来建立那个架构，
 building up that architecture,
 
 19
 00:00:48,990 --> 00:00:51,390
-但我们会尝试理解不同的方式
+但我们会尝试理解使用不同的方式
 but we'll try to understand the different ways
 
 20
 00:00:51,390 --> 00:00:52,893
-可以使用此架构。
+使用此架构。
 this architecture can be used.
 
 21
@@ -125,7 +125,7 @@ These two can be used together,
 
 26
 00:01:03,330 --> 00:01:05,330
-但它们也可以独立使用。
+也可以独立使用。
 but they can also be used independently.
 
 27
@@ -140,12 +140,12 @@ The encoder accepts inputs that represent text.
 
 29
 00:01:11,460 --> 00:01:13,620
-它转换这个文本，这些词，
+将文本中的文字
 It converts this text, these words,
 
 30
 00:01:13,620 --> 00:01:15,675
-成数值表示。
+转换成数值表示。
 into numerical representations.
 
 31
@@ -155,12 +155,12 @@ These numerical representations
 
 32
 00:01:17,400 --> 00:01:20,460
-也可以称为嵌入或特征。
+也可以称为嵌入（embeddings）或特征（features）。
 can also be called embeddings, or features.
 
 33
 00:01:20,460 --> 00:01:23,100
-我们会看到它使用了 self-attention 机制
+我们会看到它使用了自注意力（self-attention）机制
 We'll see that it uses the self-attention mechanism
 
 34
@@ -170,17 +170,17 @@ as its main component.
 
 35
 00:01:25,500 --> 00:01:27,120
-我们建议你查看视频
+我们建议您查看
 We recommend you check out the video
 
 36
 00:01:27,120 --> 00:01:29,700
-关于编码器具体要了解
+有关编码器的视频
 on encoders specifically to understand
 
 37
 00:01:29,700 --> 00:01:31,680
-这个数字表示是什么，
+特别是要了解这个数字表示是什么，
 what is this numerical representation,
 
 38
@@ -205,7 +205,7 @@ The decoder is similar to the encoder.
 
 42
 00:01:42,780 --> 00:01:45,630
-它还可以接受文本输入。
+它也可以接受文本输入。
 It can also accept text inputs.
 
 43
@@ -215,7 +215,7 @@ It uses a similar mechanism as the encoder,
 
 44
 00:01:48,210 --> 00:01:51,150
-这也是掩蔽的自我关注。
+掩蔽的自我注意力。
 which is the masked self-attention as well.
 
 45
@@ -235,17 +235,17 @@ and is traditionally used in an auto-regressive manner.
 
 48
 00:01:58,590 --> 00:02:01,650
-在这里，我们也建议你查看有关解码器的视频
+在这里，我们也建议您查看有关解码器的视频
 Here too, we recommend you check out the video on decoders
 
 49
 00:02:01,650 --> 00:02:04,000
-特别是要了解所有这些是如何工作的。
+特别是要了解这些是如何工作的。
 especially to understand how all of this works.
 
 50
 00:02:06,810 --> 00:02:07,890
-结合两部分
+结合这两部分
 Combining the two parts
 
 51
@@ -270,7 +270,7 @@ and computes a high-level representation of those inputs.
 
 55
 00:02:17,850 --> 00:02:20,252
-然后将这些输出传递给解码器。
+然后将这些作为输出传递给解码器。
 These outputs are then passed to the decoder.
 
 56
@@ -295,26 +295,27 @@ which it will re-use in future iterations,
 
 60
 00:02:30,248 --> 00:02:32,662
-因此，术语自回归。
+这也是为什么叫其自回归。
 hence the term, auto-regressive.
 
 61
 00:02:32,662 --> 00:02:34,740
-最后，为了理解
+最后，为了全面理解
 Finally, to get an understanding
 
 62
 00:02:34,740 --> 00:02:36,690
-编码器 - 解码器作为一个整体，
+编码器 - 解码器
 of the encoder-decoders as a whole,
 
 63
 00:02:36,690 --> 00:02:39,670
-我们建议你查看有关编码器 - 解码器的视频。
+我们建议您查看有关编码器 - 解码器的视频。
 we recommend you check out the video on encoder-decoders.
 
 64
 00:02:39,670 --> 00:02:42,420
-（徽标呼啸而过）
+（logo 再一次闪过）
+
 (logo whooshing)