It seems automatically transcribing chants is essentially impossible with standard speech-to-text models. Is this an #accessibility issue for deaf people wanting to participate in protests? Or are there some chant-to-text models I'm not aware of?
It seems automatically transcribing chants is essentially impossible with standard speech-to-text models. Is this an #accessibility issue for deaf people wanting to participate in protests? Or are there some chant-to-text models I'm not aware of?