A while back I had the issue of figuring out where a particular thing was said in a video or audio, so I thought "was it possible to search a video/audio ?".
I knew what the steps would look like (Transcribe -> Parse/Search Transcripts), but it was kinda hard to get really good accuracy on transcription, no that wasn't really the problem, the problem was I needed an open source STT model I could easily iterate upon freely and also wrap my head around, I tried some cloud STT/ASR's but I lacked that freedom. Then came OpenAI with Whisper, the accuracy is really good even with the tiny.en model, then another issue I had was deploying the model and creating a UI for interaction, then came Streamlit, it was really fun creating with Streamlit's widgets and then deploying on Streamlit cloud, smooth as butter.
Finally, I came up with this: Search Media Web App, I'm curious what people think about this, I really don't know what to think of it, but I'm glad I was able to solve a problem I had, so send in your feedbacks or just try it out..
Top comments (2)
Looks super-cool! And simple!
I worked with something similar from Azure - Azure Media Services. They can do Audio Indexing of a media file. They give not only the transcript, but also a bunch of other info (like OCR for video; emotion/mood recognition). But it is far from free.
Thank you, sorry I'm just seeing this..
Wow cool stuff with the Azure Media Service.. Maybe I could have a free trial on it..
Thanks for the tip