Speaker 1: hello today we are going to convert an audio into text for which we are going to use the python tool a tool that has really used us a lot with the typical of artificial intelligence we have already created a folder in this section for which we are going to create the first thing is a .pi file remember that in this case I am going to put it as add.py and for you to have this section here it is recommended that you have installed python which is the latest version if necessary simply if you go to the official python page and give the option to download and install one of the very important recommendations is that you install this program in the local disk c here we have a python folder and here are all the complements the packages that have been installed according to what we have downloaded and installed from python so it is highly recommended that you install it in that local disk folder and then we go back to our project and in the section that is here what we are going to do is first import one of the libraries we go to the arrow up here to the option up here or you can come to the option to run if not to the terminal management and a new terminal or maybe pressing ctrl eñe ctrl eñe can already finish and then what we have to go to the browser and look for this package this package that is called pin recognition and to this package that is here we are going to copy it and we go to our project and we go to the terminal of the terminals I paste it and press enter aquí esperamos que se instale todo todo el paquete que se requiere no se demora tanto ya está instalado ahora una vez creado este paquete como vamos a comenzar con la codificación de lo que vamos a crear ya lo primero que nosotros vamos a hacer es importar la librería que hemos instalado que se llama speed aquí está aquí la tenemos como ya importamos y ya la tenemos le damos un nombre que it is called cd to put it as cd and we are also going to import another of the tools that come from your country that is import time time and once you create these two tools what we are going to bring is the following function that is the same package that comes we give r is equal to what we have converted from our speed package and this is going to be the point with nice and this as it is a function we plan it in this way then for what we are going to do next is to add the route where our audio is going to bring this from this way we are going to look for what is needed in downloads in music we are going to create this route for which we are going to write which point audio file this option of audio files is not going to help us a lot here what we are going to open the we are going to open parentheses and the simple commit and then we are going to add our audio address what we are going to code first as source and two points once we have created this part of here here we are going to create a variable called audio audio and then I am going to be equal to r point ready here I am going to listen to all the audio that comes from our source file our source file and here we are going to give it a trade is like a type a trade catch more or less and let's see if it appears like this and this is a trade is that here we are going to send a message notifying the user that the quotation marks put with my simple and now yes wait a moment the audio is reading and we have a few points this is a message to identify that the audio is reading once we create this we go to the reading of the text that will not to bring the following the text comes from the point with this function we have to define as it is with google and we are going to bring what the audio is that we have declared the previous one we are going to also add the language in which language you are going to define it in this case I am going to leave it as Spanish and this is the way to translate it into Spanish and we are going to add in what time the silenced will be when the audio begins, it will be from 1.5 and then what we are going to add is to show the text that is not translating with a print and this will bring what the text is saying and in the contrary to the section that is going to be done we are going to add I do not know I did not manage to recognize the audio here this would be all the coding so far now what we are going to do is a small cut to record the audio that we are going to use the audio that we are going to use remember that it will have a very important singularity here because it will only accept this with archivo punto w a b ya entonces ya les voy a grabar el audio y lo vamos a probar una vez que usted ya tenga en el audio en mi caso ya lo tengo el audio

Speaker 2: aquí traducido aquí lo podemos escuchar mi nombre es en la valencia y estamos haciendo la prueba aquí está aquí está This is the audio that we are going to translate, so it is something very important that we

Speaker 1: know where the file is, we are going to copy the route above all, here the route is important to copy it, we come to the section here and in the section where it says with serie audio file we are going to place our route but nevertheless here we are going to make a small modification here to be able to read this audio we are going to give it a double bar in each of the parts here too and here we put the name that is called test audio dot w here so far I have managed to translate it from this file of this type of format so I recommend that the files that have point to that point m 4 m 4 to mp3 convert it to audio point w a b and once this process is done and the audio has been recorded, what we are going to do is try to convert we can go to the session from here to the one that is sorry the accession that is here run or give f5 to the little one that is here once this part is achieved we are going to translate the audio we go to the session of here from here as we were before and we are going to run and we are going to see is that it does not mark an error not so far it is not being read it does not recognize the audio to see something we ate like this here it is here we ate something we are going to execute again here it comes out that it is not reading the audio for a moment that the audio is being read and here they have to appear as it was in the audio hello how are you all greetings my name is daniel valencia and we are doing the test of converting an audio into text so let's see how it goes that is the audio that I have automatically used to be able to do this test here I leave you the audio

Speaker 3: hello how are you all my name is Thank you for watching.