How to convert text_feature into human-readable text text information

[qixuxiang]

I use clip4clip model to train my own data: I prepare my own dataset as here， and I also can run test.py

python tools/test.py configs/retrieval/clip4clip/clip4clip_vit-base-p32-res224-clip-pre_8xb16-u12-5e_msrvtt-9k-rgb.py \
    checkpoints/SOME_CHECKPOINT.pth --dump result.pkl

the result is below

    def process(self, data_batch: Optional[Dict],
                data_samples: Sequence[Dict]) -> None:
        """Process one batch of data samples and data_samples. The processed
        results should be stored in ``self.results``, which will be used to
        compute the metrics when all batches have been processed.

        Args:
            data_batch (dict, optional): A batch of data from the dataloader.
            data_samples (Sequence[dict]): A batch of outputs from the model.
        """
        data_samples = copy.deepcopy(data_samples)

        for data_sample in data_samples:
            results = dict()
            features = data_sample['features']
            video_feature = features['video_feature'].cpu().numpy()
            text_feature = features['text_feature'].cpu().numpy()
            results['video_feature'] = video_feature
            results['text_feature'] = text_feature
            self.results.append(results)

but how to convert text_feature into human-readable text text information.I'm a newbie, I'd be very grateful if I could get your reply and help. @Dai-Wenxun