=clip_len)
        ...     indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
        ...     return indices


        >>> # video clip consists of 300 frames (10 seconds at 30 FPS)
        >>> file_path = hf_hub_download(
        ...     repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
        ... )
        >>> container = av.open(file_path)

        >>> # sample 16 frames
        >>> indices = sample_frame_indices(clip_len=16, frame_sample_rate=1, seg_len=container.streams.video[0].frames)
        >>> video = read_video_pyav(container, indices)

        >>> image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")
        >>> model = VideoMAEForVideoClassification.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")

        >>> inputs = image_processor(list(video), return_tensors="pt")

        >>> with torch.no_grad():
        ...     outputs = model(**inputs)
        ...     logits = outputs.logits

        >>> # model predicts one of the 400 Kinetics-400 classes
        >>> predicted_label = logits.argmax(-1).item()
        >>> print(model.config.id2label[predicted_label])
        eating spaghetti
        ```Nrī