Error with speaker diarization and transcription

ValueError: attempt to get argmin of an empty sequence

code used:
from speechbox import ASRDiarizationPipeline
pipeline = ASRDiarizationPipeline(
asr_pipeline=asr_pipeline, diarization_pipeline=diarization_pipeline)

from transformers import pipeline

asr_pipeline = pipeline(
"automatic-speech-recognition",
model=model,
feature_extractor=feature_extractor,
tokenizer=tokenizer,
device=0
)