def __init__(self, model_name, model_path):
    super().__init__(model_name)
    self.model_path = model_path
    self.model = None

def load_model(self):
    self.model = nemo_asr.models.EncDecRNNTBPEModel.restore_from(self.model_path, map_location="mps")

def predict(self, input_paths):

    confidence_cfg = ConfidenceConfig(
        preserve_frame_confidence=True,  # Internally set to true if preserve_token_confidence == True
        # or preserve_word_confidence == True
        preserve_token_confidence=True,  # Internally set to true if preserve_word_confidence == True
        preserve_word_confidence=True,
        aggregation="prod",  # How to aggregate frame scores to token scores and token scores to word scores
        exclude_blank=False,  # If true, only non-blank emissions contribute to confidence scores
        tdt_include_duration=False,  # If true, calculate duration confidence for the TDT models
        method_cfg=ConfidenceMethodConfig(  # Config for per-frame scores calculation (before aggregation)
            name="max_prob",  # Or "entropy" (default), which usually works better
            entropy_type="gibbs",  # Used only for name == "entropy". Recommended: "tsallis" (default) or "renyi"
            alpha=0.5,  # Low values (<1) increase sensitivity, high values decrease sensitivity
            entropy_norm="lin",  # How to normalize (map to [0,1]) entropy. Default: "exp"
        ),
    )
    self.model.change_decoding_strategy(RNNTDecodingConfig(fused_batch_size=-1, strategy="greedy_batch", confidence_cfg=confidence_cfg))

    transcriptions = self.model.transcribe(
        audio=input_paths, return_hypotheses=True
    )
    
    fastconformer_transcriptions = [x for x in transcriptions][0]

    return fastconformer_transcriptions