1 00:00:00,000 --> 00:00:19,000 This is an instruction video on how you can run the transcription with the software Whisper on audio data inside TSD. 2 00:00:19,000 --> 00:00:31,000 I will continue in this video that you have a TSD project that you have managed to log into. 3 00:00:31,000 --> 00:00:39,000 What we are going to do first is to copy the Whisper software via a server. 4 00:00:39,000 --> 00:00:48,000 To log in to the server, you must go into a shell and log in to the server. 5 00:00:48,000 --> 00:00:59,000 We use PuTTY in this example. There are several options, but we use PuTTY, which is inside all Windows machines in TSD. 6 00:00:59,000 --> 00:01:05,000 To find it, I can use search and search for PuTTY. 7 00:01:05,000 --> 00:01:10,000 I start PuTTY and it looks like this. 8 00:01:10,000 --> 00:01:18,000 What we are going to log in to now is a machine called Submit. 9 00:01:18,000 --> 00:01:23,000 In front of Submit, you must enter your project number. 10 00:01:23,000 --> 00:01:33,000 For me, in this example, it will be p896-submit. 11 00:01:33,000 --> 00:01:40,000 This is the server I'm going to log in to to run the commands and copy the software. 12 00:01:40,000 --> 00:01:56,000 I press open and log in as my user. 13 00:01:56,000 --> 00:02:02,000 In here, I have to run some Unix commands. 14 00:02:02,000 --> 00:02:14,000 What I do in my example is that I want to find the Durable map, because that's where I want to put Whisper on the computer. 15 00:02:14,000 --> 00:02:21,000 Default, I came into a user map. To see where it is, I can type p-double-d. 16 00:02:21,000 --> 00:02:24,000 Then I see that it is a home area. 17 00:02:24,000 --> 00:02:32,000 I can go into Durable and type cd-prick-prick. Then I come up one level. 18 00:02:32,000 --> 00:02:38,000 Then I can do it again and type p-b-d. 19 00:02:38,000 --> 00:02:41,000 Then I see that I'm right in my project. 20 00:02:41,000 --> 00:02:45,000 If I type ls, I can get some areas here. 21 00:02:45,000 --> 00:02:52,000 Then I know that if I type cd-data, then I come into data and can check again with ls. 22 00:02:52,000 --> 00:02:58,000 Then I see that I have Durable. I type cd-durable. 23 00:02:58,000 --> 00:03:11,000 I can do an ls and I see that I recognize my, for example, network attachments and network data folders that I have in Durable today. 24 00:03:11,000 --> 00:03:22,000 Now I'm going to copy this Whisper catalog, which is in a shared folder on a server, into this area. 25 00:03:22,000 --> 00:03:27,000 Until then, everyone must run this software locally. 26 00:03:27,000 --> 00:03:43,000 What can be done is to simply copy the command that is in the video and paste it. 27 00:03:43,000 --> 00:03:51,000 Because it is a copy command called cp-r to be able to have with some sub-catalogs. 28 00:03:51,000 --> 00:03:54,000 It is in the shared software Whisper. 29 00:03:54,000 --> 00:04:05,000 It is very copied. If it says in the middle of a point, it will end up where I am right now, which is in the Durable folder. 30 00:04:05,000 --> 00:04:17,000 This means that the catalog is now copied right under Durable. 31 00:04:17,000 --> 00:04:27,000 This will take some time, as there are some gigabytes of data, but that was it. 32 00:04:27,000 --> 00:04:34,000 Now I would like to go over to use explorers, because that's what you can do with File Explorer. 33 00:04:34,000 --> 00:04:36,000 You have probably used it before. 34 00:04:36,000 --> 00:04:42,000 I can go into my data folder on Durable. 35 00:04:42,000 --> 00:04:46,000 There is now a catalog called Whisper. 36 00:04:46,000 --> 00:04:54,000 Inside this catalog, there is now a script and a program. 37 00:04:54,000 --> 00:04:58,000 You can see that there is something called large.pt. 38 00:04:58,000 --> 00:05:01,000 This is the largest output of Whisper, which needs the most possible data power. 39 00:05:01,000 --> 00:05:07,000 In this case, it is the one with the best solution. 40 00:05:07,000 --> 00:05:10,000 We think that's the best right now. 41 00:05:10,000 --> 00:05:20,000 The data folder is mapped and the script is set up to take all the files that are in the folder and transcribe them. 42 00:05:20,000 --> 00:05:24,000 I'm going to find some data and I have some data that I have ready. 43 00:05:24,000 --> 00:05:27,000 A sound file and a video file. 44 00:05:27,000 --> 00:05:35,000 I can copy that and go into the data folder and paste them in. 45 00:05:35,000 --> 00:05:46,000 Now I want these to be transcribed and I have to run the script called transcribe data. 46 00:05:46,000 --> 00:05:55,000 This script can only be run from the Linux server that I have logged in to. 47 00:05:55,000 --> 00:05:59,000 I can't run it in Windows Explorer, but on this right server. 48 00:05:59,000 --> 00:06:11,000 It is important that you have access to Colossus, i.e. the IT system, to be allowed to run this program. 49 00:06:11,000 --> 00:06:18,000 The way to run this program is to write.score or transcribe data. 50 00:06:18,000 --> 00:06:25,000 The command is together with the video here and you can paste it into PuTTY. 51 00:06:25,000 --> 00:06:31,000 You can always paste data into TST, but you can't copy data out. 52 00:06:31,000 --> 00:06:34,000 That's a trick to get commands. 53 00:06:34,000 --> 00:06:49,000 If I run the command now, which is.score or transcribe data. 54 00:06:49,000 --> 00:06:58,000 I got an error message here, but when I type.pbd it is because I'm in the wrong folder. 55 00:06:58,000 --> 00:07:03,000 So I have to type cd whisper. 56 00:07:03,000 --> 00:07:06,000 I have to be in the whisper catalog. 57 00:07:06,000 --> 00:07:17,000 If I type the same command now, it says submitted batch job and a number. 58 00:07:17,000 --> 00:07:26,000 It means that it has been put in queue at the computer on Colossus. 59 00:07:26,000 --> 00:07:28,000 I have to wait for it to be finished. 60 00:07:28,000 --> 00:07:42,000 This can depend on the traffic on the computer and how many files you have put into transcription. 61 00:07:42,000 --> 00:07:47,000 Here I have put in both a sound file and a movie file. 62 00:07:47,000 --> 00:08:04,000 Then it's just a matter of waiting a little while and I can check in the file explorer if this has arrived. 63 00:08:04,000 --> 00:08:18,000 After a while, I can go into the folder data in the explorer and there I see that there are now three files. 64 00:08:18,000 --> 00:08:22,000 Each file that I have put in. 65 00:08:22,000 --> 00:08:28,000 This is what whisper today automatically sets up. 66 00:08:28,000 --> 00:08:34,000 It's a text file, a VTT file and a SRT file. 67 00:08:34,000 --> 00:08:41,000 With that I say good luck to transcribe data into TST. 68 00:08:41,000 --> 00:08:49,000 It's smart to take all the data from here and move them afterwards so that you don't transcribe everything again. 69 00:08:49,000 --> 00:08:54,000 Because in the data folder there must always be finished data. 70 00:08:54,000 --> 00:09:08,000 I can cut this and then I could just make a folder here called finished data, for example. 71 00:09:08,000 --> 00:09:12,000 And then I could say that I put those files there. 72 00:09:12,000 --> 00:09:21,000 So that I know that when I run the script, everything that is in the data folder is transcribed. 73 00:09:21,000 --> 00:09:24,000 Good luck.