Understanding Model Capabilities

[HardikJain02]

Inference: python3 inference.py --face examples/face/1.mp4 --audio examples/audio/1.wav --outfile results/1_1.mp4

Question 1: Are below cases possible?

Case 1

• Input: --face argument has a 10-second video with its own audio, and --audio argument has 5 minutes of audio.
• Output: Expecting a 5-minute video with the provided 5-minute audio.

Case 2

• Input: --face argument has a 10-second video without audio, and --audio argument has 5 minutes of audio.
• Output: Expecting a 5-minute video with the provided 5-minute audio.

Question 2: What is the longest duration that can be achieved by the shortest input video with and without audio?