1
00:00:00,930 --> 00:00:02,890
- [Presenter] In this
video, I'm going to discuss

2
00:00:02,890 --> 00:00:06,530
the first three imports that
you see here, each of which

3
00:00:06,530 --> 00:00:09,310
is from the IBM Watson Module

4
00:00:09,310 --> 00:00:12,910
from the Watson Developer Cloud SDK.

5
00:00:12,910 --> 00:00:15,190
Now, if by any chance
you're following along

6
00:00:15,190 --> 00:00:17,627
with these videos in our book

7
00:00:17,627 --> 00:00:20,947
"Python for Programmers" or our textbook

8
00:00:20,947 --> 00:00:24,260
"Intro to Python for Computer
Science and Data Science"

9
00:00:24,260 --> 00:00:26,340
in the book you're going to see here,

10
00:00:26,340 --> 00:00:28,750
instead of IBM underscore watson,

11
00:00:28,750 --> 00:00:33,370
you'll see watson underscore
developer underscore cloud.

12
00:00:33,370 --> 00:00:36,410
And that's because they
renamed the module since

13
00:00:36,410 --> 00:00:37,350
we published the book.

14
00:00:37,350 --> 00:00:41,670
However, the code as is in
the book will also work.

15
00:00:41,670 --> 00:00:44,920
So they still have
backwards compatibility.

16
00:00:44,920 --> 00:00:47,910
Now you'll notice we've
imported three classes from

17
00:00:47,910 --> 00:00:49,760
the IBM Watson Module.

18
00:00:49,760 --> 00:00:54,720
The class called Speech to
Text V1 is the first version

19
00:00:54,720 --> 00:00:58,080
of their speech to text
class that accesses

20
00:00:58,080 --> 00:01:00,950
the Watson Speech to Text service for you.

21
00:01:00,950 --> 00:01:04,170
And as you're going to see
in the code down below,

22
00:01:04,170 --> 00:01:06,900
with simple method calls on this object,

23
00:01:06,900 --> 00:01:10,660
we are going to be able
to submit an audio file

24
00:01:10,660 --> 00:01:13,180
off to the speech to text service.

25
00:01:13,180 --> 00:01:17,070
It will then transcribe that
text for us, assuming it's

26
00:01:17,070 --> 00:01:20,020
in a language that the
service understands.

27
00:01:20,020 --> 00:01:23,470
And what it's going to give
us back is a JSON document

28
00:01:23,470 --> 00:01:26,710
that contains the text
transcription, which we of course

29
00:01:26,710 --> 00:01:31,090
will then access and pull
out of that JSON object.

30
00:01:31,090 --> 00:01:34,540
We have the Language
Translator service version 3.

31
00:01:34,540 --> 00:01:38,960
So this class encapsulates
everything that needs to be done

32
00:01:38,960 --> 00:01:42,930
to communicate with Watson's
Language Translator.

33
00:01:42,930 --> 00:01:46,780
And again, we'll take texts,
in this case, hand it off

34
00:01:46,780 --> 00:01:48,970
to the language translator service,

35
00:01:48,970 --> 00:01:51,060
and what it will give us back, once again,

36
00:01:51,060 --> 00:01:55,260
is a JSON document containing
the translated text.

37
00:01:55,260 --> 00:01:56,870
And, of course, this assumes

38
00:01:56,870 --> 00:01:59,630
that it's supported languages once again.

39
00:01:59,630 --> 00:02:03,710
And finally, we have the
class Text to Speech V1,

40
00:02:03,710 --> 00:02:07,650
and for that one, we're
going to give it text,

41
00:02:07,650 --> 00:02:11,120
which we then want to
turn into an audio file.

42
00:02:11,120 --> 00:02:14,740
And what it's going to give
us back is the audio file

43
00:02:14,740 --> 00:02:17,970
that we can then play back in our app.

44
00:02:17,970 --> 00:02:21,300
So, we'll see the use of
each of these three classes

45
00:02:21,300 --> 00:02:24,270
as we take a look in a
couple of videos from now

46
00:02:24,270 --> 00:02:27,363
at the run translator
method, or function rather.