I tested audio transcription from OpenAI Whisper on Raspberry PI. The results were astonishing!

Рет қаралды 5,725

Күн бұрын

Пікірлер: 10

@Ul_Nika 4 ай бұрын

wow! great experiment! At the end, I also wondered about the accuracy, so if it's an interesting topic for you I will be grateful for your sharing.

@itkacher 4 ай бұрын

Thank you! You can see the accuracy on 10:57 kzbin.info/www/bejne/pnmTaKCknJedeLcsi=pGX2A9TTy_gcHFqc&t=657 . The most common differences is punctuation, lowercase/upper case. However, I didn't test the real-live scenario. The youtube video has a professional sound with a speach from a professional actor. I don't know the quality of the transcription if it happens in the noised spaces 😂 I'll let you know if I try it :)

@3DForge-i7i 2 ай бұрын

Would it be easy to pass the transcription to lama to summarize it, create task list, etc… ?

@itkacher 2 ай бұрын

It shouldn’t be a problem. There are a lot of technical issues with the transcription as the Whisper tries to transcribe sounds that aren’t voices. But I haven’t tried this.

@3DForge-i7i 2 ай бұрын

@@itkacheryeah but I meant on the RPI itself with a lama instance which may run on the Hailo ?

@itkacher 2 ай бұрын

I haven’t try llama. I saw that people run it on CPU. It was very slow. Sorry, I have no idea if it supports Hailo.

@cedricrueckert2399 4 ай бұрын

nice work!! so if you would put the text to translate this and give that as sound out... you would have the first life translation. If you do such project im highly interested so see the results :)

@itkacher 4 ай бұрын

Thank you! To be honest, there are plenty of such solutions on the market. Just Google "ai live translation". However, it's not so simple, and the devil is in the details. The transcription worked perfectly fine on a speech from Netflix. In real life, sounds and noises will add some false words. Additionally, a narrator's quality does matters. Then, the translation works great, but it also produces a lot of false-translation. So it will work, but the quality wouldn't be so good. And the process require something more powerful, like Nvidia Jetson, Xavier, etc.