feat: Enhanced compatibility and performance in ShotRS2VPipeline

[GACLove]

by moving generated video/audio segments to CPU and converting to float format before appending.

[gemini-code-assist]

Code Review

This pull request updates rs2v_infer.py to move video and audio segments to the CPU and cast video segments to float before appending them to result lists. The review feedback points out a redundant .clone() call on the video segment and recommends adding a .float() conversion to the audio segment for consistency.

[gemini-code-assist]

The implementation can be improved for efficiency and consistency:

1. Redundant .clone(): On line 158, video_seg.clone() is unnecessary. Moving a tensor to CPU via .cpu() already creates a new copy. Since video_seg is a slice, .cpu() will only transfer the relevant data, making the GPU-side clone redundant.
2. Consistency with PR description: The PR description mentions converting segments to float format before appending. This is missing for the audio segment on line 159. Adding .float() ensures consistency and aligns with the PR's objective.

Note: Applying these changes will make the subsequent conversions at lines 168 and 170 redundant, which you may want to clean up as well.

Suggested change

	gen_video_list.append(video_seg.clone().cpu().float())
	cut_audio_list.append(audio_seg.cpu())
	gen_video_list.append(video_seg.cpu().float())
	cut_audio_list.append(audio_seg.cpu().float())