src/evaluate/evaluator/base.py [246:268]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        pipe = self.prepare_pipeline(
            model_or_pipeline=model_or_pipeline,
            tokenizer=tokenizer,
            feature_extractor=feature_extractor,
            device=device,
        )
        metric = self.prepare_metric(metric)

        # Compute predictions
        predictions, perf_results = self.call_pipeline(pipe, pipe_inputs)
        predictions = self.predictions_processor(predictions, label_mapping)

        metric_inputs.update(predictions)

        # Compute metrics from references and predictions
        metric_results = self.compute_metric(
            metric=metric,
            metric_inputs=metric_inputs,
            strategy=strategy,
            confidence_level=confidence_level,
            n_resamples=n_resamples,
            random_state=random_state,
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/evaluate/evaluator/text_classification.py [134:155]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        pipe = self.prepare_pipeline(
            model_or_pipeline=model_or_pipeline,
            tokenizer=tokenizer,
            feature_extractor=feature_extractor,
            device=device,
        )
        metric = self.prepare_metric(metric)

        # Compute predictions
        predictions, perf_results = self.call_pipeline(pipe, pipe_inputs)
        predictions = self.predictions_processor(predictions, label_mapping)
        metric_inputs.update(predictions)

        # Compute metrics from references and predictions
        metric_results = self.compute_metric(
            metric=metric,
            metric_inputs=metric_inputs,
            strategy=strategy,
            confidence_level=confidence_level,
            n_resamples=n_resamples,
            random_state=random_state,
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -