vllm/tests/models/fixtures/audioflamingo3/expected_results_batched.json

{"transcriptions": ["There is no clear relationship between the barking and the music, as they seem to be independent of each other.", "(B) To indicate that language cannot express clearly, satirizing the inversion of black and white in the world"], "token_ids": [[3862, 374, 902, 2797, 5025, 1948, 279, 293, 33452, 323, 279, 4627, 11, 438, 807, 2803, 311, 387, 9489, 315, 1817, 1008, 13, 151645], [5349, 8, 2014, 13216, 429, 4128, 4157, 3158, 9355, 11, 7578, 404, 4849, 279, 46488, 315, 3691, 323, 4158, 304, 279, 1879, 151645, 151671]]}