Demo of audio transcriber application
HTML-код
- Опубликовано: 22 авг 2024
- This video is a demonstration of the alpha version of an application that I developed that allows to transcribe audio record into text. I utilized Whisper-1, a speech transcription model developed by OpenAI (the creators of ChatGPT) to build this application.
It cost me only 0.06 cents per minute of audio transcribed and it has high level of accuracy for 57 different languages including English, French, Spanish, Arabic, Portuguese, and Swahili.
How it works? Start by capturing your audio using your smartphone. Once you have the audio file in hand, it's time to move to the next step. Simply transfer the audio file from your smartphone to your computer. This sets the stage for real magic. As you open the application, with just three clicks in sequence, you can effortlessly load, transform, and transcribe the audio.
Very nice.
Congratulations🎉
What did you use to create this app? Do you have the exe file
I used Tkinter. Yes, I have a executable file. For now it is the alpha version
I need an app that can translate audio in real time from portagues language to English. Is there any application like this?
As I explained in the description of this video, I utilized Whisper-1 text to speech engine ( developed by OpenAI) for transcribe and then build this Application using Tkinter. You can then use the same engine and the translations API takes as input the audio file in any of the supported languages and transcribes, if necessary, the audio into English. This differs from /Transcriptions endpoint since the output is not in the original input language and is instead translated to English text. Being said my App for now doesn't do translation but this is something that is totally possible. Perhaps it is a good idea for further improvement by adding a window/feature for translation into English.
@@AnalyzeIt_Nael I need it for learning Power BI but most of the best content I found is in Portuguese language.