use device_number for setting GPU

fix error in device index for summarizer

add summarizer to handler

update description in README.nd

add generate_answer for long form question answering https://github.com/atilatech/atila-core-service/pull/7

add support for query to be a string or an array of sentences that need encoding

allow query to handle simple strings

fix bug for when transcript length is 1 and combine_transcripts was skipping last segment by using len()-1

add sentence transformer to inference endpoint

add sentence transformers to requirements

add video info to transcript

removed tokens array from transcripts

set self.model to loaded model

fixed pt should be pytube

fixed error in verbose and time transcription

fixed documentation

add pytube to requirements.txt

change handler to use whisper model and include segments

Duplicate from philschmid/openai-whisper-endpoint