Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
ZennyKenny 
posted an update 12 days ago
Post
395
On-demand audio transcription is an often-requested service without many good options on the market.

Using Hugging Face Spaces with Gradio SDK and the OpenAI Whisper model, I've put together a simple interface that supports the transcription and summarisation of audio files up to five minutes in length, completely open source and running on CPU upgrade. The cool thing is that it's built without a dedicated inference endpoint, completely on public infrastructure.

Check it out: ZennyKenny/AudioTranscribe

I wrote a short article about the backend mechanics for those who are interested: https://huggingface.co/blog/ZennyKenny/on-demand-public-transcription
tracylwilliams93

This sounds like a fantastic project! On-demand audio transcription and summarization are such valuable tools, and it’s impressive that you’ve made it open source and functional on public infrastructure. It’s great to see innovative uses of the Hugging Face Spaces and OpenAI Whisper model. Speaking of useful tools, platforms like corrlinks https://corrlinks.pissedconsumer.com/review.html are another example of how technology is making communication and data sharing more accessible, especially in unique circumstances.

In this post