1
00:00:00,940 --> 00:00:02,480
- [Instructor] In this and
the next several videos

2
00:00:02,480 --> 00:00:04,840
we're going to walk our way
through all the source code

3
00:00:04,840 --> 00:00:09,200
in the SimpleLanguageTranslator.py
Script file.

4
00:00:09,200 --> 00:00:10,830
Now as you're about to see

5
00:00:10,830 --> 00:00:13,670
we've broken down the ten steps

6
00:00:13,670 --> 00:00:15,140
that I just discussed with you

7
00:00:15,140 --> 00:00:18,970
in the preceding video
in the code as well.

8
00:00:18,970 --> 00:00:21,740
So in the code you're
actually going to see

9
00:00:21,740 --> 00:00:23,490
comments with the step numbers

10
00:00:23,490 --> 00:00:25,530
so in step one we're going to prompt for

11
00:00:25,530 --> 00:00:27,770
and then record the English audio file

12
00:00:27,770 --> 00:00:32,010
then in step two we'll
transcribe that English to text

13
00:00:32,010 --> 00:00:33,950
and English text specifically.

14
00:00:33,950 --> 00:00:35,970
Then we'll translate that English text

15
00:00:35,970 --> 00:00:38,881
and then we'll synthesize an audio file

16
00:00:38,881 --> 00:00:43,480
in which we use the Spanish
text to create audio

17
00:00:43,480 --> 00:00:46,990
that can be spoken to the
person we are conversing with.

18
00:00:46,990 --> 00:00:49,900
So in these steps two, three and four

19
00:00:49,900 --> 00:00:51,920
are where we're going to see the calls

20
00:00:51,920 --> 00:00:54,760
to the IBM Watson web services

21
00:00:54,760 --> 00:00:57,040
and we're going to do that through

22
00:00:57,040 --> 00:01:01,090
the Watson Developer
Cloud sdk capabilities

23
00:01:01,090 --> 00:01:03,860
that we'll import into our script file.

24
00:01:03,860 --> 00:01:06,410
And then of course in
step five once we have the

25
00:01:06,410 --> 00:01:10,600
synthesized Spanish we will
play back that audio file.

26
00:01:10,600 --> 00:01:14,530
And then we'll have a
separate chunk of code again

27
00:01:14,530 --> 00:01:15,926
for the other steps,

28
00:01:15,926 --> 00:01:18,945
five additional steps that
do basically the same thing

29
00:01:18,945 --> 00:01:20,640
in the reverse order.

30
00:01:20,640 --> 00:01:24,170
In this case we'll get the
Spanish speech into an audio file

31
00:01:24,170 --> 00:01:27,440
transcribe that Spanish
speech into Spanish text,

32
00:01:27,440 --> 00:01:30,370
take the Spanish text
into English text via

33
00:01:30,370 --> 00:01:32,680
IBM Watson's Translation Service

34
00:01:32,680 --> 00:01:35,130
and then finally take the English text

35
00:01:35,130 --> 00:01:38,990
and convert it into spoken
audio that we can play back

36
00:01:38,990 --> 00:01:39,823
to the user.