About length of audio input to the model

#73
by sanjitaa - opened

I am using inference API of this largev2 model but the problem is it only transcribes audio of 3o sec. I want to transcribe the audio more than 30 sec through inference API of this model . How to solve this ?

Please help me out with it..

I don't think it's possible with the current inference API: https://huggingface.co./docs/api-inference/detailed_parameters#automatic-speech-recognition-task

Maybe @reach-vb can advise on how to bypass this?

@reach-vb If there is any solution for this please help me out because I am using inference API for transcription not other methods.

Sign up or log in to comment