Hopefully new advances in AI will let you try new things with your old recordings
> How's the audio quality on those devices you link to in other comments?
Decent, quality is directly proportional to the distance between the microphone and the mouth, but can't expect too much from 30$ devices.
>and always struggled to come up with a viable algorithm and model to differentiate "background chatter" from the main conversation
Yes, that's a big problem to solve, you can try Pyannote's Diarization https://lablab.ai/t/whisper-transcription-and-speaker-identi...
that will be a next step for the experience
Hopefully new advances in AI will let you try new things with your old recordings
> How's the audio quality on those devices you link to in other comments?
Decent, quality is directly proportional to the distance between the microphone and the mouth, but can't expect too much from 30$ devices.
>and always struggled to come up with a viable algorithm and model to differentiate "background chatter" from the main conversation
Yes, that's a big problem to solve, you can try Pyannote's Diarization https://lablab.ai/t/whisper-transcription-and-speaker-identi...
that will be a next step for the experience