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.
Tracy Williams
tracylwilliams93
AI & ML interests
None yet
Recent Activity
replied to
ZennyKenny's
post
11 days ago
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: https://huggingface.co./spaces/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
Organizations
None yet
tracylwilliams93's activity
replied to
ZennyKenny's
post
11 days ago
This Text2Image 3D Generator v2.0 update is incredible! Faster generation and better quality are going to make such a difference for projects like game design and marketing visuals. It reminds me of some of the beautifully designed e-cards from Jacquie Lawson https://jacquie-lawson.pissedconsumer.com/customer-service.html —I've seen a few that look like they might even use 3D-generated elements.