DIY, Maker, Hacker, Science Experiments
I am going to explain 2 methods to upload large files to Colab. And there is a problem in Google Colab, or maybe it is a restriction, that does not allow to upload files larger than 1Mb using its graphical interface.
It is very useful for those who are going to work with Whisper, since any audio file weighs more than 1MB.
When uploading a file, it starts to load, takes a long time and at the end the upload disappears or only 1Mb of our file is uploaded, leaving it incomplete.
Colaboratory, also called Google Colab is a product of Google Research and is used to write and run Python and other languages from your browser.
Here is a beginner’s guide that perfectly complements this article.
Colab is a hosted Jupyter, installed and configured, so that we do not have to do anything on our computer but simply work from the browser, on cloud resources.
It works exactly like Jupyter. They are Notebooks or notebooks based on cells that can be texts, images or code, in this Python step, because unlike Jupyter Colab at the moment you can only use the Python kernel, they talk about implementing later others like R, Scala, etc, but no date is said.
TinyML or Tiny Machine Learning refers to the use of Machine Learning in microcontrollers. In systems that unlike those used in traditional ML have few resources, are systems that have little CPU, little RAM and extremely low power consumption in the order of magnitude of milliwatts or microwatts.
Its official website is the TinyML Foundation.
What is done is to reduce large models for use with equipment with very few resources and microcontrollers. The preferred field of the Makers.
This is one guide to learn about Stable Diffusion and teach how you can use this tool.
The image above is generated with Stable Diffusion. It has been generated from the following text (prompt)
City skyline with skycrapers, by Stanislav Sidorov, digital art, ultra realistic, ultra detailed, photorealistic, 4k, character concept, soft light, blade runner, futuristic
Stable Diffusion is a text-to-image machine learning model. A deep learning model, of artificial intelligence that allows us to generate images from text that we put as input or input.
It’s not the first model or the first tool of this style, right now there’s a lot of talk about Dall-e 2, MidJourney, Google Image, but it is the most important because of what it represents. Stable Diffusion is an Open Source project, so anyone can use and modify it. In version 1.4 we have a 4G .cpxt file where the entire pre-trained model comes from, and this is a real revolution.
So much so that in just 2 or 3 weeks since its release, we find plugins for PhotoShop, GIMP, Krita, WordPress, Blender, etc. pretty much every tool that comes with images is implementing Stable Diffusion, so much so that even competitors like Midjourney are using it to enhance their tools. But it is not only used to generate tools, but we as users can install it on our PC and run it to obtain the images locally.
Because in addition to being Open Source does not mean that it is less powerful than the previous ones. It is a true wonder. For me right now it is the best tool that we can use if we want to generate our images for any project.
There are different ways to use it. Right now I recommend 2. If your computer has the necessary power, that is, a graphics card with about 8Gb of RAM, then install it on your computer. If your hardware is not powerful enough use a Google Collab, right now I recommend the Altryne one, because it comes with a graphical interface and is easier to use.
step to detail.
This is the option that I recommend if your computer is not powerful enough (GPU with 8Gb of RAM) or if you want to try it with all its features without having to install anything.
I recommend it because it has a very comfortable graphical interface with many options to control the images and other model tools such as image to image and upscale.
We use the Google colab created by Altryne and Google Drive to save the model and the results.
It’s all free. I leave a video of the whole process that as you will see is very simple.
The idea of the project is give voice instructions to interact through our PC or our Raspberry Pi using the Voice-to-text Whisper model.
We will give an order that will be transcribed, converted to text, with Whisper and then analyzed to execute the appropriate order, which can be from executing a program to giving voltage to the RaspberryPi pins.
I am going to use an old Raspberry Pi 2, a micro USB and I will use the Voice-to-text model recently released by OpenAI, Whisper. At the end of the article you can see a little more whisper.
One of the most laborious tasks in Machine Learning consists of data collection and treatment.
There are a meteorological observatory in my city. You can see main meteorological indicators in real time trough its we and it share historical data too, but it share it in PDF
I have talk with them in order to share all data in CSV and allow people to use the data easily, but it seems that is not possible 🙁
Therefore I want this data and I want to convert this PDF files to a workable data collection. And I have been searching a good solution to convert this table PDF to CSV and the solution is called Canvas.
Once you have data in CSV you can use this data in many ways, opening with excel, Libre office, Google Sheets, etc, because is easy import them in spreedsheets or using pythons and its libraries.
As I want an automatized process I will work with a python script and is here where I introduce Tabula.
This article is an Anaconda installation guide and also a guide of its packages manager, Conda. With this technology we will be able to create development environment for Python and R with the libraries we prefer. It is very interesting to begin learn Machine Learning, data analysis and programming with Python.
Anaconda is a Free and Open Source distribution for Python and R languages. It is very used in Data Science, Machine Learning, Science, Engineering, predictive analytics,Big Data, etc
Installing Anaconda we can use a great quantity of packages. There are more than 1400 of the most known applications and software. Some examples are: