Added test for multilingual option with english-german audio
I've already removed output_language argument as it is redundant, you can get the same functionality with task="translate" and I've verified this with several model sizes
use the correct encoder_output for language detection
enabled the same functionality for batched inference
Summary:
multilingualoption with english-german audiooutput_languageargument as it is redundant, you can get the same functionality withtask="translate"and I've verified this with several model sizesencoder_outputfor language detection