Best FREE Speech to Text AI – Software Whisper AI

In this step-by-step Article , learn how to utilize OpenAI’s Whisper AI to transcribe and transform voice or audio into text. Whisper AI works incredibly well and better than most human transcribers. It also surpasses most other voice to text technologies in most scenarios.

WAHT IS WHISPER AI

Whisper is a general-purpose voice recognition model. It is trained on a vast dataset of different sounds and is also a multitasking model that can do multilingual voice recognition, speech translation, and language identification.

INSTALL GOOGLE COLABORATORY

01- Visit Google Drive and establish your Google account if you don’t already have one setup.
02- In the upper left hand corner, click the New button-> More->Connect more apps.

03- In the search area at the top of the dialog, put in Google Colaboratory and search.
04- Select the first option “Colaboratory”

05- Click the Install button, then Click Continue and press OK to the button that Google Colaboratory is linked to Google Drive.
06- Colaboratory has been installed.
07- Click the Done button and shut down the “Connect more apps” box.
08- You have now installed Google Colaboratory.

CONFIGURE GOOGLE COLABORATORY

01- Visit Google Drive and establish your Google account if you don’t already have one setup.
02- In the upper left hand corner, click the New button-> More->Colaboratory.

03- This opens Colaboratory.
04- In the upper left hand corner, give the file a name by choosing Untitled.ipynb and renaming it to something more meaningful.
05- Click the “Runtime” menu and choose “Change runtime type” to open the “Notebook settings” dialog

06- Set the “Hardware accelerator” to “GPU”. This will configure it to utilize the graphics card where Whisper AI performs best.
07- You have now setup Google Colaboratory.

INSTALL WHISPER AI ON GOOGLE COLABORATORY

1. After following the previous steps in Google Colaboratory, open Colaboratory.
2. Paste in the following code into the Colaboratory editor to install whisper and ffmpeg(support for audio and video files) to Colaboratory:
   !pip install git+https://github.com/openai/whisper.git
!sudo apt update && sudo apt install ffmpeg
   
3. Select Run icon to run the code to install Whisper and ffmpeg. It should take ~20 seconds.

RUN WHISPER AI

1. After following the previous steps in Google Colaboratory, open Colaboratory.
2. Click the Folder icon on the left hand navigation menu
3. Drag and drop in the audio or video you want to transcribe.
4. Click “OK” to the “Reminder, uploaded files will get deleted when this runtime is recycled.” dialog box.
5. The file has been uploaded and you should see it under the Folder menu in the left navigation menu.
6. Click to the code menu and paste in the following code to run Whisper on the file :
   !whisper "ENTER FILE NAME HERE" --model medium.en
   • Replace “ENTER FILE NAME HERE” with the name of the file you want to transcribe.
   • Replace medium.en with the model you would like to use- tiny, base, small, medium or large where tiny is the fastest, smallest and with the least accuracy and large takes longer, is a larger file and with highest quality model.
7. Click the Run icon to run the code.
   
8. You can see the transcript. You can also see 3 files added to the Folder- FILE.mp3.srt, FILE.mp3.txt and FILE.mp3.vtt files
   • FILE.mp3.txt contains all the text from the audio
   • FILE.mp3.vtt and FILE.mp3.srt are caption formats with timestamps
9. To download the files, hover over the FILE.mp3.*, select the ellipsis menu and select Download.