Hardik Jain

Real-Time Implementation of Seamless Expressive

1

Anyone can help me with how to implement seamless expressive in real-time with no latency ? Also, Suggest me some code references to implement. I am also interested in learning...

ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (5,) + inhomogeneous part.

3

I crash into this error while executing python test.py --trained_model=craft_mlt_25k.pth --refiner_model=craft_refiner_CTW1500.pth --test_folder=myfolder --refine Traceback (most recent call last): File "C:\code\CRAFT-pytorch\test.py", line 165, in bboxes, polys, score_text = test_net(net, image, args.text_threshold,...

Is there any way to detect the text color without knowing about the background color of it in the bbox? @ku21fan @tgalkovskyi @coallaoh @akarazniewicz

I want to detect the color of the text in the original image. Any possible ways?

How do I proceed next to get the text? [I am a noob]

3

If the following is the code for whisper (it is for local video), what will be the code for yt-whisper for a youtube video? import whisper model = whisper.load_model("base") result...

**At 00:10** the lip alignment is not right. Are there any possibilities to make it better? @kunncheng @vinthony https://github.com/OpenTalker/video-retalking/assets/69311953/f6876858-52bf-451f-aa3b-52765c9dadbc

**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...

I want to map each corresponding points in the point cloud to its 2d counterpart.

Infinite Depth

3

Room having bright windows tends to have infinite depth, hence non-desirable results. Any workaround?

Trained on custom data still getting May Lady's face in my output.

2

I wonder why this lady's face is there? **Trained on this video:** https://www.youtube.com/watch?v=tv-YUsK2Xsw [Removed yellow shirt guy from the video] **Output video:** https://github.com/ZiqiaoPeng/SyncTalk/assets/69311953/553de1f4-4931-4609-a60c-acf3485d7211 My model directory looks like this: **[Working...