After All Is Said and Indexed – Unlocking Information in Recorded Speech
1–10 of 17 posts
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#2A really interesting blog post I found using LLMs for audio search which I think is a pretty nifty/new idea.
I've found it cumbersome using some of the new vector DBs (chroma, faiss, etc) to make end to end systems, but with Marqo it doesn't seem too hard.
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#3Both speaker and speech recognition are done in the article using huggingface.
Is there anything as good ready to use on-prem for the diarization (speaker recognition)?
I've heard good things about whisper(.cpp) for speech recognition and vosk used to be king of that hill...
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#4Hadn't heard of the thing they were putting their data into, Marqo, a "tensor search for humans" ,
https://github.com/marqo-ai/marqo
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#5Both speaker and speech recognition are done in the article using huggingface. Is there anything as good ready to use on-prem for the diarization (speaker recognition)? I've heard good things about whisper(.cpp) for speech recognition and vosk used to be king of that hill...
Diarization can be done on premise using pyannote (what they use in the article). Huggingface offers a library to run things locally and an API to run things on their cloud. Pyannote is available under an MIT licence
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#6A really interesting blog post I found using LLMs for audio search which I think is a pretty nifty/new idea. I've found it cumbersome using some of the new vector DBs (chroma, faiss, etc) to make end to end systems, but with Marqo it doesn't seem too hard.
> I've found it cumbersome using some of the new vector DBs (chroma, faiss, etc) to make end to end systems
What parts are cumbersome?
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#7Both speaker and speech recognition are done in the article using huggingface. Is there anything as good ready to use on-prem for the diarization (speaker recognition)? I've heard good things about whisper(.cpp) for speech recognition and vosk used to be king of that hill...
vosk is really good, but also a good example of an open source project with great potential, but doesn't scale up because the person behind it is a douchebag.
documentation is poor, and what you find is sparsed outdated shit on the web, so it's really hard to find help.
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#8How does this compare to using Whisper and feeding that into a vector DB and querying with a LLM
Pardon the dumb question I only have an elementary understanding
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#9This is interesting but what problem does it solve better than CTRL+F-ing a transcript? It seems like this would be a worse solution for when the precise way someone says something could be important (ex. journalists parsing an interview, students studying their recorded lectures) and that it would be most useful if you were working with a large volume of recorded audio, such as customer service calls. This makes me somewhat uncomfortable, but perhaps I am not fully understanding how it works.
Edit: wording
Re: After All Is Said and Indexed – Unlocking Information in Recorded Speech
#10This is interesting but what problem does it solve better than CTRL+F-ing a transcript? It seems like this would be a worse solution for when the precise way someone says something could be important (ex. journalists parsing an interview, students studying their recorded lectures) and that it would be most useful if you were working with a large volume of recorded audio, such as customer service calls. This makes me…
> This is interesting but what problem does it solve better than CTRL+F-ing a transcript?
Producing the transcript?
Being able to classify and search data seems like a pretty big deal these days too.