douwantech / musetalk
Real-Time High Quality Lip Synchronization with Latent Space Inpainting
Prediction
douwantech/musetalk:5501004e78525e4bbd9fa20d1e75ad51fddce5a274bec07b9b16d685e34eeaf8ID5d25am1qjsrgj0cfwy6v07mqg0StatusSucceededSourceWebHardwareA40Total durationCreatedInput
- fps
- 25
- bbox_shift
- 0
- audio_input
- Video Player is loading.Current Time 00:00:000/Duration 00:00:000Loaded: 0%00:00:000Stream Type LIVERemaining Time -00:00:0001x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
- video_input
{ "fps": 25, "bbox_shift": 0, "audio_input": "https://replicate.delivery/pbxt/L2hFThsgfNCT3ZaqOoez3T2foFrCiQTw3ihjDoOHikWVdYGK/sun.wav", "video_input": "https://replicate.delivery/pbxt/L2hFUyTjQUalIvUBRskwEaJLCi1dwbWNMjL1NI9cQNgvMfaX/sun.mp4" }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run douwantech/musetalk using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "douwantech/musetalk:5501004e78525e4bbd9fa20d1e75ad51fddce5a274bec07b9b16d685e34eeaf8", { input: { fps: 25, bbox_shift: 0, audio_input: "https://replicate.delivery/pbxt/L2hFThsgfNCT3ZaqOoez3T2foFrCiQTw3ihjDoOHikWVdYGK/sun.wav", video_input: "https://replicate.delivery/pbxt/L2hFUyTjQUalIvUBRskwEaJLCi1dwbWNMjL1NI9cQNgvMfaX/sun.mp4" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run douwantech/musetalk using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "douwantech/musetalk:5501004e78525e4bbd9fa20d1e75ad51fddce5a274bec07b9b16d685e34eeaf8", input={ "fps": 25, "bbox_shift": 0, "audio_input": "https://replicate.delivery/pbxt/L2hFThsgfNCT3ZaqOoez3T2foFrCiQTw3ihjDoOHikWVdYGK/sun.wav", "video_input": "https://replicate.delivery/pbxt/L2hFUyTjQUalIvUBRskwEaJLCi1dwbWNMjL1NI9cQNgvMfaX/sun.mp4" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run douwantech/musetalk using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "douwantech/musetalk:5501004e78525e4bbd9fa20d1e75ad51fddce5a274bec07b9b16d685e34eeaf8", "input": { "fps": 25, "bbox_shift": 0, "audio_input": "https://replicate.delivery/pbxt/L2hFThsgfNCT3ZaqOoez3T2foFrCiQTw3ihjDoOHikWVdYGK/sun.wav", "video_input": "https://replicate.delivery/pbxt/L2hFUyTjQUalIvUBRskwEaJLCi1dwbWNMjL1NI9cQNgvMfaX/sun.mp4" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-06-05T08:42:59.554296Z", "created_at": "2024-06-05T08:39:02.806000Z", "data_removed": false, "error": null, "id": "5d25am1qjsrgj0cfwy6v07mqg0", "input": { "fps": 25, "bbox_shift": 0, "audio_input": "https://replicate.delivery/pbxt/L2hFThsgfNCT3ZaqOoez3T2foFrCiQTw3ihjDoOHikWVdYGK/sun.wav", "video_input": "https://replicate.delivery/pbxt/L2hFUyTjQUalIvUBRskwEaJLCi1dwbWNMjL1NI9cQNgvMfaX/sun.mp4" }, "logs": "please download ffmpeg-static and export to FFMPEG_PATH.\nFor example: export FFMPEG_PATH=/musetalk/ffmpeg-4.4-amd64-static\nLoads checkpoint by local backend from path: ./models/dwpose/dw-ll_ucoco_384.pth\ncuda start\nDownloading: \"https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth\" to /root/.cache/torch/hub/checkpoints/s3fd-619a316812.pth\n 0%| | 0.00/85.7M [00:00<?, ?B/s]\n 0%| | 32.0k/85.7M [00:00<08:18, 180kB/s]\n 0%| | 80.0k/85.7M [00:00<06:21, 235kB/s]\n 0%| | 176k/85.7M [00:00<03:58, 376kB/s] \n 0%| | 384k/85.7M [00:00<02:09, 690kB/s]\n 1%| | 784k/85.7M [00:00<01:10, 1.26MB/s]\n 2%|▏ | 1.56M/85.7M [00:01<00:36, 2.40MB/s]\n 4%|▎ | 3.14M/85.7M [00:01<00:18, 4.60MB/s]\n 5%|▌ | 4.59M/85.7M [00:01<00:14, 5.76MB/s]\n 9%|▉ | 7.83M/85.7M [00:01<00:08, 9.84MB/s]\n 13%|█▎ | 11.0M/85.7M [00:01<00:06, 12.4MB/s]\n 17%|█▋ | 14.2M/85.7M [00:01<00:05, 14.4MB/s]\n 20%|██ | 17.5M/85.7M [00:02<00:04, 15.7MB/s]\n 24%|██▍ | 20.8M/85.7M [00:02<00:04, 16.8MB/s]\n 28%|██▊ | 24.2M/85.7M [00:02<00:03, 17.6MB/s]\n 32%|███▏ | 27.7M/85.7M [00:02<00:03, 18.3MB/s]\n 36%|███▋ | 31.1M/85.7M [00:02<00:03, 18.8MB/s]\n 40%|████ | 34.5M/85.7M [00:03<00:02, 19.2MB/s]\n 44%|████▍ | 38.1M/85.7M [00:03<00:02, 19.6MB/s]\n 49%|████▊ | 41.8M/85.7M [00:03<00:02, 20.1MB/s]\n 53%|█████▎ | 45.4M/85.7M [00:03<00:02, 20.5MB/s]\n 57%|█████▋ | 49.1M/85.7M [00:03<00:01, 23.6MB/s]\n 60%|██████ | 51.5M/85.7M [00:03<00:01, 23.3MB/s]\n 63%|██████▎ | 53.8M/85.7M [00:04<00:01, 19.9MB/s]\n 66%|██████▌ | 56.6M/85.7M [00:04<00:01, 20.1MB/s]\n 68%|██████▊ | 58.6M/85.7M [00:04<00:01, 15.9MB/s]\n 71%|███████ | 60.9M/85.7M [00:04<00:01, 15.1MB/s]\n 74%|███████▍ | 63.6M/85.7M [00:04<00:01, 15.3MB/s]\n 78%|███████▊ | 66.4M/85.7M [00:04<00:01, 15.5MB/s]\n 81%|████████ | 69.2M/85.7M [00:05<00:01, 15.7MB/s]\n 84%|████████▍ | 72.0M/85.7M [00:05<00:00, 15.8MB/s]\n 87%|████████▋ | 74.8M/85.7M [00:05<00:00, 15.9MB/s]\n 91%|█████████ | 77.6M/85.7M [00:05<00:00, 16.0MB/s]\n 94%|█████████▍| 80.5M/85.7M [00:05<00:00, 16.2MB/s]\n 97%|█████████▋| 83.3M/85.7M [00:06<00:00, 16.2MB/s]\n100%|██████████| 85.7M/85.7M [00:06<00:00, 14.9MB/s]\nRUN: predict\nvideo in 25.0 FPS, audio idx in 50FPS\nextracting landmarks...time consuming\nreading images...\n 0%| | 0/550 [00:00<?, ?it/s]\n 3%|▎ | 18/550 [00:00<00:03, 174.06it/s]\n 7%|▋ | 36/550 [00:00<00:03, 168.18it/s]\n 10%|▉ | 53/550 [00:00<00:03, 162.51it/s]\n 13%|█▎ | 70/550 [00:00<00:02, 160.83it/s]\n 16%|█▌ | 87/550 [00:00<00:02, 158.52it/s]\n 19%|█▊ | 103/550 [00:00<00:02, 158.65it/s]\n 22%|██▏ | 119/550 [00:00<00:02, 158.15it/s]\n 25%|██▍ | 135/550 [00:00<00:02, 155.39it/s]\n 27%|██▋ | 151/550 [00:00<00:02, 153.15it/s]\n 30%|███ | 167/550 [00:01<00:02, 151.41it/s]\n 33%|███▎ | 183/550 [00:01<00:02, 150.10it/s]\n 36%|███▌ | 199/550 [00:01<00:02, 150.23it/s]\n 39%|███▉ | 215/550 [00:01<00:02, 152.64it/s]\n 42%|████▏ | 231/550 [00:01<00:02, 153.88it/s]\n 45%|████▍ | 247/550 [00:01<00:01, 154.31it/s]\n 48%|████▊ | 264/550 [00:01<00:01, 158.29it/s]\n 51%|█████ | 281/550 [00:01<00:01, 160.09it/s]\n 54%|█████▍ | 298/550 [00:01<00:01, 160.41it/s]\n 57%|█████▋ | 315/550 [00:02<00:01, 159.41it/s]\n 60%|██████ | 331/550 [00:02<00:01, 158.80it/s]\n 63%|██████▎ | 347/550 [00:02<00:01, 157.95it/s]\n 66%|██████▌ | 363/550 [00:02<00:01, 158.17it/s]\n 69%|██████▉ | 379/550 [00:02<00:01, 156.87it/s]\n 72%|███████▏ | 395/550 [00:02<00:00, 155.70it/s]\n 75%|███████▍ | 411/550 [00:02<00:00, 153.27it/s]\n 78%|███████▊ | 427/550 [00:02<00:00, 152.61it/s]\n 81%|████████ | 443/550 [00:02<00:00, 152.02it/s]\n 83%|████████▎ | 459/550 [00:02<00:00, 151.55it/s]\n 86%|████████▋ | 475/550 [00:03<00:00, 149.60it/s]\n 89%|████████▉ | 491/550 [00:03<00:00, 151.32it/s]\n 92%|█████████▏| 508/550 [00:03<00:00, 154.69it/s]\n 95%|█████████▌| 525/550 [00:03<00:00, 156.66it/s]\n 99%|█████████▊| 542/550 [00:03<00:00, 157.67it/s]\n100%|██████████| 550/550 [00:03<00:00, 156.02it/s]\nget key_landmark and face bounding boxes with the default value\n 0%| | 0/550 [00:00<?, ?it/s]\n 0%| | 1/550 [00:00<05:41, 1.61it/s]\n 1%| | 3/550 [00:00<01:54, 4.79it/s]\n 1%| | 5/550 [00:00<01:11, 7.59it/s]\n 1%|▏ | 7/550 [00:00<00:55, 9.83it/s]\n 2%|▏ | 9/550 [00:01<00:46, 11.70it/s]\n 2%|▏ | 11/550 [00:01<00:41, 13.01it/s]\n 2%|▏ | 13/550 [00:01<00:37, 14.41it/s]\n 3%|▎ | 15/550 [00:01<00:35, 15.17it/s]\n 3%|▎ | 17/550 [00:01<00:33, 15.76it/s]\n 3%|▎ | 19/550 [00:01<00:33, 15.78it/s]\n 4%|▍ | 21/550 [00:01<00:33, 16.02it/s]\n 4%|▍ | 23/550 [00:01<00:32, 16.14it/s]\n 5%|▍ | 25/550 [00:02<00:31, 16.42it/s]\n 5%|▍ | 27/550 [00:02<00:31, 16.64it/s]\n 5%|▌ | 29/550 [00:02<00:31, 16.69it/s]\n 6%|▌ | 31/550 [00:02<00:31, 16.66it/s]\n 6%|▌ | 33/550 [00:02<00:31, 16.50it/s]\n 6%|▋ | 35/550 [00:02<00:30, 16.64it/s]\n 7%|▋ | 37/550 [00:02<00:30, 16.76it/s]\n 7%|▋ | 39/550 [00:02<00:30, 16.78it/s]\n 7%|▋ | 41/550 [00:03<00:30, 16.59it/s]\n 8%|▊ | 43/550 [00:03<00:31, 16.28it/s]\n 8%|▊ | 45/550 [00:03<00:31, 16.20it/s]\n 9%|▊ | 47/550 [00:03<00:31, 16.09it/s]\n 9%|▉ | 49/550 [00:03<00:32, 15.58it/s]\n 9%|▉ | 51/550 [00:03<00:31, 15.75it/s]\n 10%|▉ | 53/550 [00:03<00:31, 15.57it/s]\n 10%|█ | 55/550 [00:03<00:31, 15.69it/s]\n 10%|█ | 57/550 [00:04<00:30, 16.40it/s]\n 11%|█ | 59/550 [00:04<00:29, 16.47it/s]\n 11%|█ | 61/550 [00:04<00:30, 16.27it/s]\n 11%|█▏ | 63/550 [00:04<00:29, 16.41it/s]\n 12%|█▏ | 65/550 [00:04<00:29, 16.43it/s]\n 12%|█▏ | 67/550 [00:04<00:29, 16.11it/s]\n 13%|█▎ | 69/550 [00:04<00:29, 16.34it/s]\n 13%|█▎ | 71/550 [00:04<00:28, 16.52it/s]\n 13%|█▎ | 73/550 [00:04<00:29, 16.41it/s]\n 14%|█▎ | 75/550 [00:05<00:28, 16.46it/s]\n 14%|█▍ | 77/550 [00:05<00:28, 16.73it/s]\n 14%|█▍ | 79/550 [00:05<00:28, 16.72it/s]\n 15%|█▍ | 81/550 [00:05<00:27, 16.88it/s]\n 15%|█▌ | 83/550 [00:05<00:27, 16.94it/s]\n 15%|█▌ | 85/550 [00:05<00:28, 16.59it/s]\n 16%|█▌ | 87/550 [00:05<00:27, 16.91it/s]\n 16%|█▌ | 89/550 [00:05<00:27, 16.84it/s]\n 17%|█▋ | 91/550 [00:06<00:27, 16.93it/s]\n 17%|█▋ | 93/550 [00:06<00:26, 17.12it/s]\n 17%|█▋ | 95/550 [00:06<00:26, 17.23it/s]\n 18%|█▊ | 97/550 [00:06<00:26, 17.02it/s]\n 18%|█▊ | 99/550 [00:06<00:27, 16.21it/s]\n 18%|█▊ | 101/550 [00:06<00:27, 16.23it/s]\n 19%|█▊ | 103/550 [00:06<00:27, 16.32it/s]\n 19%|█▉ | 105/550 [00:06<00:26, 16.57it/s]\n 19%|█▉ | 107/550 [00:07<00:26, 16.55it/s]\n 20%|█▉ | 109/550 [00:07<00:26, 16.45it/s]\n 20%|██ | 111/550 [00:07<00:26, 16.47it/s]\n 21%|██ | 113/550 [00:07<00:26, 16.52it/s]\n 21%|██ | 115/550 [00:07<00:26, 16.47it/s]\n 21%|██▏ | 117/550 [00:07<00:26, 16.60it/s]\n 22%|██▏ | 119/550 [00:07<00:25, 16.66it/s]\n 22%|██▏ | 121/550 [00:07<00:25, 16.58it/s]\n 22%|██▏ | 123/550 [00:07<00:25, 16.89it/s]\n 23%|██▎ | 125/550 [00:08<00:24, 17.02it/s]\n 23%|██▎ | 127/550 [00:08<00:24, 17.23it/s]\n 23%|██▎ | 129/550 [00:08<00:24, 17.53it/s]\n 24%|██▍ | 131/550 [00:08<00:24, 17.40it/s]\n 24%|██▍ | 133/550 [00:08<00:23, 17.50it/s]\n 25%|██▍ | 135/550 [00:08<00:23, 17.66it/s]\n 25%|██▍ | 137/550 [00:08<00:23, 17.72it/s]\n 25%|██▌ | 139/550 [00:08<00:23, 17.42it/s]\n 26%|██▌ | 141/550 [00:09<00:24, 16.88it/s]\n 26%|██▌ | 143/550 [00:09<00:23, 16.98it/s]\n 26%|██▋ | 145/550 [00:09<00:23, 16.96it/s]\n 27%|██▋ | 147/550 [00:09<00:23, 17.13it/s]\n 27%|██▋ | 149/550 [00:09<00:23, 16.74it/s]\n 27%|██▋ | 151/550 [00:09<00:23, 17.07it/s]\n 28%|██▊ | 153/550 [00:09<00:23, 17.03it/s]\n 28%|██▊ | 155/550 [00:09<00:23, 16.98it/s]\n 29%|██▊ | 157/550 [00:09<00:23, 17.06it/s]\n 29%|██▉ | 159/550 [00:10<00:22, 17.34it/s]\n 29%|██▉ | 161/550 [00:10<00:22, 17.28it/s]\n 30%|██▉ | 163/550 [00:10<00:22, 17.34it/s]\n 30%|███ | 165/550 [00:10<00:22, 17.19it/s]\n 30%|███ | 167/550 [00:10<00:22, 17.13it/s]\n 31%|███ | 169/550 [00:10<00:22, 16.95it/s]\n 31%|███ | 171/550 [00:10<00:21, 17.28it/s]\n 31%|███▏ | 173/550 [00:10<00:22, 17.09it/s]\n 32%|███▏ | 175/550 [00:11<00:21, 17.09it/s]\n 32%|███▏ | 177/550 [00:11<00:21, 16.99it/s]\n 33%|███▎ | 179/550 [00:11<00:21, 17.01it/s]\n 33%|███▎ | 181/550 [00:11<00:21, 17.25it/s]\n 33%|███▎ | 183/550 [00:11<00:21, 17.14it/s]\n 34%|███▎ | 185/550 [00:11<00:21, 16.82it/s]\n 34%|███▍ | 187/550 [00:11<00:21, 16.87it/s]\n 34%|███▍ | 189/550 [00:11<00:21, 16.86it/s]\n 35%|███▍ | 191/550 [00:11<00:21, 17.03it/s]\n 35%|███▌ | 193/550 [00:12<00:21, 16.89it/s]\n 35%|███▌ | 195/550 [00:12<00:21, 16.76it/s]\n 36%|███▌ | 197/550 [00:12<00:21, 16.59it/s]\n 36%|███▌ | 199/550 [00:12<00:21, 16.69it/s]\n 37%|███▋ | 201/550 [00:12<00:20, 16.90it/s]\n 37%|███▋ | 203/550 [00:12<00:20, 16.93it/s]\n 37%|███▋ | 205/550 [00:12<00:20, 16.75it/s]\n 38%|███▊ | 207/550 [00:12<00:20, 16.60it/s]\n 38%|███▊ | 209/550 [00:13<00:20, 16.38it/s]\n 38%|███▊ | 211/550 [00:13<00:21, 16.11it/s]\n 39%|███▊ | 213/550 [00:13<00:20, 16.08it/s]\n 39%|███▉ | 215/550 [00:13<00:20, 16.11it/s]\n 39%|███▉ | 217/550 [00:13<00:20, 16.05it/s]\n 40%|███▉ | 219/550 [00:13<00:20, 16.53it/s]\n 40%|████ | 221/550 [00:13<00:19, 16.64it/s]\n 41%|████ | 223/550 [00:13<00:19, 16.66it/s]\n 41%|████ | 225/550 [00:14<00:19, 16.71it/s]\n 41%|████▏ | 227/550 [00:14<00:19, 16.98it/s]\n 42%|████▏ | 229/550 [00:14<00:19, 16.80it/s]\n 42%|████▏ | 231/550 [00:14<00:18, 16.98it/s]\n 42%|████▏ | 233/550 [00:14<00:18, 17.23it/s]\n 43%|████▎ | 235/550 [00:14<00:18, 17.37it/s]\n 43%|████▎ | 237/550 [00:14<00:17, 17.49it/s]\n 43%|████▎ | 239/550 [00:14<00:17, 17.38it/s]\n 44%|████▍ | 241/550 [00:14<00:17, 17.18it/s]\n 44%|████▍ | 243/550 [00:15<00:17, 17.16it/s]\n 45%|████▍ | 245/550 [00:15<00:17, 17.23it/s]\n 45%|████▍ | 247/550 [00:15<00:17, 17.26it/s]\n 45%|████▌ | 249/550 [00:15<00:17, 17.11it/s]\n 46%|████▌ | 251/550 [00:15<00:17, 17.22it/s]\n 46%|████▌ | 253/550 [00:15<00:17, 17.09it/s]\n 46%|████▋ | 255/550 [00:15<00:17, 16.62it/s]\n 47%|████▋ | 257/550 [00:15<00:17, 16.76it/s]\n 47%|████▋ | 259/550 [00:16<00:17, 16.69it/s]\n 47%|████▋ | 261/550 [00:16<00:17, 16.93it/s]\n 48%|████▊ | 263/550 [00:16<00:16, 17.01it/s]\n 48%|████▊ | 265/550 [00:16<00:16, 17.15it/s]\n 49%|████▊ | 267/550 [00:16<00:16, 17.25it/s]\n 49%|████▉ | 269/550 [00:16<00:16, 16.82it/s]\n 49%|████▉ | 271/550 [00:16<00:16, 17.22it/s]\n 50%|████▉ | 273/550 [00:16<00:16, 17.13it/s]\n 50%|█████ | 275/550 [00:16<00:16, 17.02it/s]\n 50%|█████ | 277/550 [00:17<00:15, 17.12it/s]\n 51%|█████ | 279/550 [00:17<00:15, 17.12it/s]\n 51%|█████ | 281/550 [00:17<00:15, 17.05it/s]\n 51%|█████▏ | 283/550 [00:17<00:15, 16.91it/s]\n 52%|█████▏ | 285/550 [00:17<00:15, 16.79it/s]\n 52%|█████▏ | 287/550 [00:17<00:15, 16.95it/s]\n 53%|█████▎ | 289/550 [00:17<00:15, 16.97it/s]\n 53%|█████▎ | 291/550 [00:17<00:15, 16.94it/s]\n 53%|█████▎ | 293/550 [00:17<00:15, 16.94it/s]\n 54%|█████▎ | 295/550 [00:18<00:14, 17.17it/s]\n 54%|█████▍ | 297/550 [00:18<00:14, 17.21it/s]\n 54%|█████▍ | 299/550 [00:18<00:14, 17.11it/s]\n 55%|█████▍ | 301/550 [00:18<00:14, 17.07it/s]\n 55%|█████▌ | 303/550 [00:18<00:14, 16.66it/s]\n 55%|█████▌ | 305/550 [00:18<00:14, 16.72it/s]\n 56%|█████▌ | 307/550 [00:18<00:14, 16.99it/s]\n 56%|█████▌ | 309/550 [00:18<00:14, 17.19it/s]\n 57%|█████▋ | 311/550 [00:19<00:13, 17.41it/s]\n 57%|█████▋ | 313/550 [00:19<00:13, 17.49it/s]\n 57%|█████▋ | 315/550 [00:19<00:13, 17.67it/s]\n 58%|█████▊ | 317/550 [00:19<00:13, 17.49it/s]\n 58%|█████▊ | 319/550 [00:19<00:13, 16.79it/s]\n 58%|█████▊ | 321/550 [00:19<00:13, 16.94it/s]\n 59%|█████▊ | 323/550 [00:19<00:13, 17.03it/s]\n 59%|█████▉ | 325/550 [00:19<00:13, 16.82it/s]\n 59%|█████▉ | 327/550 [00:19<00:13, 16.73it/s]\n 60%|█████▉ | 329/550 [00:20<00:12, 17.09it/s]\n 60%|██████ | 331/550 [00:20<00:13, 16.81it/s]\n 61%|██████ | 333/550 [00:20<00:12, 16.75it/s]\n 61%|██████ | 335/550 [00:20<00:13, 16.45it/s]\n 61%|██████▏ | 337/550 [00:20<00:12, 16.56it/s]\n 62%|██████▏ | 339/550 [00:20<00:12, 16.48it/s]\n 62%|██████▏ | 341/550 [00:20<00:12, 16.19it/s]\n 62%|██████▏ | 343/550 [00:20<00:13, 15.91it/s]\n 63%|██████▎ | 345/550 [00:21<00:12, 16.46it/s]\n 63%|██████▎ | 347/550 [00:21<00:12, 16.69it/s]\n 63%|██████▎ | 349/550 [00:21<00:11, 16.89it/s]\n 64%|██████▍ | 351/550 [00:21<00:11, 17.10it/s]\n 64%|██████▍ | 353/550 [00:21<00:11, 17.34it/s]\n 65%|██████▍ | 355/550 [00:21<00:11, 17.63it/s]\n 65%|██████▍ | 357/550 [00:21<00:11, 17.49it/s]\n 65%|██████▌ | 359/550 [00:21<00:10, 17.58it/s]\n 66%|██████▌ | 361/550 [00:22<00:11, 17.11it/s]\n 66%|██████▌ | 363/550 [00:22<00:10, 17.30it/s]\n 66%|██████▋ | 365/550 [00:22<00:10, 17.43it/s]\n 67%|██████▋ | 367/550 [00:22<00:10, 17.32it/s]\n 67%|██████▋ | 369/550 [00:22<00:10, 17.19it/s]\n 67%|██████▋ | 371/550 [00:22<00:10, 16.99it/s]\n 68%|██████▊ | 373/550 [00:22<00:10, 16.98it/s]\n 68%|██████▊ | 375/550 [00:22<00:10, 16.95it/s]\n 69%|██████▊ | 377/550 [00:22<00:10, 16.67it/s]\n 69%|██████▉ | 379/550 [00:23<00:10, 17.06it/s]\n 69%|██████▉ | 381/550 [00:23<00:09, 17.27it/s]\n 70%|██████▉ | 383/550 [00:23<00:09, 17.03it/s]\n 70%|███████ | 385/550 [00:23<00:09, 16.97it/s]\n 70%|███████ | 387/550 [00:23<00:09, 16.81it/s]\n 71%|███████ | 389/550 [00:23<00:09, 16.80it/s]\n 71%|███████ | 391/550 [00:23<00:09, 16.65it/s]\n 71%|███████▏ | 393/550 [00:23<00:09, 16.90it/s]\n 72%|███████▏ | 395/550 [00:24<00:09, 17.00it/s]\n 72%|███████▏ | 397/550 [00:24<00:08, 17.22it/s]\n 73%|███████▎ | 399/550 [00:24<00:08, 17.25it/s]\n 73%|███████▎ | 401/550 [00:24<00:08, 16.94it/s]\n 73%|███████▎ | 403/550 [00:24<00:08, 16.86it/s]\n 74%|███████▎ | 405/550 [00:24<00:08, 17.08it/s]\n 74%|███████▍ | 407/550 [00:24<00:08, 17.22it/s]\n 74%|███████▍ | 409/550 [00:24<00:08, 17.32it/s]\n 75%|███████▍ | 411/550 [00:24<00:07, 17.38it/s]\n 75%|███████▌ | 413/550 [00:25<00:07, 17.29it/s]\n 75%|███████▌ | 415/550 [00:25<00:07, 17.70it/s]\n 76%|███████▌ | 417/550 [00:25<00:07, 17.79it/s]\n 76%|███████▌ | 419/550 [00:25<00:07, 17.67it/s]\n 77%|███████▋ | 421/550 [00:25<00:07, 17.73it/s]\n 77%|███████▋ | 423/550 [00:25<00:07, 17.77it/s]\n 77%|███████▋ | 425/550 [00:25<00:07, 17.55it/s]\n 78%|███████▊ | 427/550 [00:25<00:06, 17.70it/s]\n 78%|███████▊ | 429/550 [00:25<00:06, 17.62it/s]\n 78%|███████▊ | 431/550 [00:26<00:06, 17.88it/s]\n 79%|███████▊ | 433/550 [00:26<00:06, 18.13it/s]\n 79%|███████▉ | 435/550 [00:26<00:06, 18.17it/s]\n 79%|███████▉ | 437/550 [00:26<00:06, 18.19it/s]\n 80%|███████▉ | 439/550 [00:26<00:06, 17.96it/s]\n 80%|████████ | 441/550 [00:26<00:06, 18.12it/s]\n 81%|████████ | 443/550 [00:26<00:06, 17.68it/s]\n 81%|████████ | 445/550 [00:26<00:05, 17.69it/s]\n 81%|████████▏ | 447/550 [00:26<00:05, 17.87it/s]\n 82%|████████▏ | 449/550 [00:27<00:05, 17.75it/s]\n 82%|████████▏ | 451/550 [00:27<00:05, 17.47it/s]\n 82%|████████▏ | 453/550 [00:27<00:05, 17.48it/s]\n 83%|████████▎ | 455/550 [00:27<00:05, 17.51it/s]\n 83%|████████▎ | 457/550 [00:27<00:05, 17.75it/s]\n 83%|████████▎ | 459/550 [00:27<00:05, 17.68it/s]\n 84%|████████▍ | 461/550 [00:27<00:05, 17.66it/s]\n 84%|████████▍ | 463/550 [00:27<00:04, 17.73it/s]\n 85%|████████▍ | 465/550 [00:27<00:04, 17.65it/s]\n 85%|████████▍ | 467/550 [00:28<00:04, 17.23it/s]\n 85%|████████▌ | 469/550 [00:28<00:04, 17.32it/s]\n 86%|████████▌ | 471/550 [00:28<00:04, 17.63it/s]\n 86%|████████▌ | 473/550 [00:28<00:04, 17.60it/s]\n 86%|████████▋ | 475/550 [00:28<00:04, 17.11it/s]\n 87%|████████▋ | 477/550 [00:28<00:04, 16.55it/s]\n 87%|████████▋ | 479/550 [00:28<00:04, 16.67it/s]\n 87%|████████▋ | 481/550 [00:28<00:04, 16.70it/s]\n 88%|████████▊ | 483/550 [00:29<00:03, 16.78it/s]\n 88%|████████▊ | 485/550 [00:29<00:03, 16.90it/s]\n 89%|████████▊ | 487/550 [00:29<00:03, 17.05it/s]\n 89%|████████▉ | 489/550 [00:29<00:03, 17.18it/s]\n 89%|████████▉ | 491/550 [00:29<00:03, 17.34it/s]\n 90%|████████▉ | 493/550 [00:29<00:03, 17.63it/s]\n 90%|█████████ | 495/550 [00:29<00:03, 17.49it/s]\n 90%|█████████ | 497/550 [00:29<00:03, 17.39it/s]\n 91%|█████████ | 499/550 [00:29<00:02, 17.13it/s]\n 91%|█████████ | 501/550 [00:30<00:02, 16.85it/s]\n 91%|█████████▏| 503/550 [00:30<00:02, 16.73it/s]\n 92%|█████████▏| 505/550 [00:30<00:02, 16.76it/s]\n 92%|█████████▏| 507/550 [00:30<00:02, 17.15it/s]\n 93%|█████████▎| 509/550 [00:30<00:02, 17.16it/s]\n 93%|█████████▎| 511/550 [00:30<00:02, 17.47it/s]\n 93%|█████████▎| 513/550 [00:30<00:02, 17.32it/s]\n 94%|█████████▎| 515/550 [00:30<00:02, 16.90it/s]\n 94%|█████████▍| 517/550 [00:31<00:01, 16.98it/s]\n 94%|█████████▍| 519/550 [00:31<00:01, 17.06it/s]\n 95%|█████████▍| 521/550 [00:31<00:01, 16.94it/s]\n 95%|█████████▌| 523/550 [00:31<00:01, 16.73it/s]\n 95%|█████████▌| 525/550 [00:31<00:01, 16.93it/s]\n 96%|█████████▌| 527/550 [00:31<00:01, 17.17it/s]\n 96%|█████████▌| 529/550 [00:31<00:01, 16.94it/s]\n 97%|█████████▋| 531/550 [00:31<00:01, 16.79it/s]\n 97%|█████████▋| 533/550 [00:31<00:01, 16.71it/s]\n 97%|█████████▋| 535/550 [00:32<00:00, 16.53it/s]\n 98%|█████████▊| 537/550 [00:32<00:00, 16.61it/s]\n 98%|█████████▊| 539/550 [00:32<00:00, 16.65it/s]\n 98%|█████████▊| 541/550 [00:32<00:00, 16.42it/s]\n 99%|█████████▊| 543/550 [00:32<00:00, 15.93it/s]\n 99%|█████████▉| 545/550 [00:32<00:00, 16.15it/s]\n 99%|█████████▉| 547/550 [00:32<00:00, 16.41it/s]\n100%|█████████▉| 549/550 [00:32<00:00, 16.41it/s]\n100%|██████████| 550/550 [00:33<00:00, 16.66it/s]\n********************************************bbox_shift parameter adjustment**********************************************************\nTotal frame:「550」 Manually adjust range : [ -9~9 ] , the current value: 0\n*************************************************************************************************************************************\nstart inference\n 0%| | 0/71 [00:00<?, ?it/s]\n 1%|▏ | 1/71 [00:02<02:23, 2.05s/it]\n 3%|▎ | 2/71 [00:02<01:09, 1.01s/it]\n 4%|▍ | 3/71 [00:02<00:46, 1.48it/s]\n 6%|▌ | 4/71 [00:02<00:34, 1.93it/s]\n 7%|▋ | 5/71 [00:03<00:28, 2.29it/s]\n 8%|▊ | 6/71 [00:03<00:24, 2.60it/s]\n 10%|▉ | 7/71 [00:03<00:22, 2.85it/s]\n 11%|█▏ | 8/71 [00:04<00:20, 3.04it/s]\n 13%|█▎ | 9/71 [00:04<00:19, 3.19it/s]\n 14%|█▍ | 10/71 [00:04<00:18, 3.29it/s]\n 15%|█▌ | 11/71 [00:04<00:17, 3.38it/s]\n 17%|█▋ | 12/71 [00:05<00:17, 3.44it/s]\n 18%|█▊ | 13/71 [00:05<00:16, 3.48it/s]\n 20%|█▉ | 14/71 [00:05<00:16, 3.52it/s]\n 21%|██ | 15/71 [00:05<00:15, 3.53it/s]\n 23%|██▎ | 16/71 [00:06<00:15, 3.52it/s]\n 24%|██▍ | 17/71 [00:06<00:15, 3.55it/s]\n 25%|██▌ | 18/71 [00:06<00:14, 3.56it/s]\n 27%|██▋ | 19/71 [00:07<00:14, 3.56it/s]\n 28%|██▊ | 20/71 [00:07<00:14, 3.56it/s]\n 30%|██▉ | 21/71 [00:07<00:14, 3.56it/s]\n 31%|███ | 22/71 [00:07<00:13, 3.58it/s]\n 32%|███▏ | 23/71 [00:08<00:13, 3.59it/s]\n 34%|███▍ | 24/71 [00:08<00:13, 3.57it/s]\n 35%|███▌ | 25/71 [00:08<00:12, 3.57it/s]\n 37%|███▋ | 26/71 [00:09<00:12, 3.56it/s]\n 38%|███▊ | 27/71 [00:09<00:12, 3.56it/s]\n 39%|███▉ | 28/71 [00:09<00:12, 3.55it/s]\n 41%|████ | 29/71 [00:09<00:11, 3.56it/s]\n 42%|████▏ | 30/71 [00:10<00:11, 3.55it/s]\n 44%|████▎ | 31/71 [00:10<00:11, 3.57it/s]\n 45%|████▌ | 32/71 [00:10<00:10, 3.56it/s]\n 46%|████▋ | 33/71 [00:11<00:10, 3.56it/s]\n 48%|████▊ | 34/71 [00:11<00:10, 3.55it/s]\n 49%|████▉ | 35/71 [00:11<00:10, 3.55it/s]\n 51%|█████ | 36/71 [00:11<00:09, 3.56it/s]\n 52%|█████▏ | 37/71 [00:12<00:09, 3.57it/s]\n 54%|█████▎ | 38/71 [00:12<00:09, 3.56it/s]\n 55%|█████▍ | 39/71 [00:12<00:08, 3.56it/s]\n 56%|█████▋ | 40/71 [00:12<00:08, 3.57it/s]\n 58%|█████▊ | 41/71 [00:13<00:08, 3.56it/s]\n 59%|█████▉ | 42/71 [00:13<00:08, 3.58it/s]\n 61%|██████ | 43/71 [00:13<00:07, 3.58it/s]\n 62%|██████▏ | 44/71 [00:14<00:07, 3.56it/s]\n 63%|██████▎ | 45/71 [00:14<00:07, 3.56it/s]\n 65%|██████▍ | 46/71 [00:14<00:07, 3.55it/s]\n 66%|██████▌ | 47/71 [00:14<00:06, 3.55it/s]\n 68%|██████▊ | 48/71 [00:15<00:06, 3.54it/s]\n 69%|██████▉ | 49/71 [00:15<00:06, 3.57it/s]\n 70%|███████ | 50/71 [00:15<00:05, 3.57it/s]\n 72%|███████▏ | 51/71 [00:16<00:05, 3.58it/s]\n 73%|███████▎ | 52/71 [00:16<00:05, 3.58it/s]\n 75%|███████▍ | 53/71 [00:16<00:05, 3.60it/s]\n 76%|███████▌ | 54/71 [00:16<00:04, 3.60it/s]\n 77%|███████▋ | 55/71 [00:17<00:04, 3.60it/s]\n 79%|███████▉ | 56/71 [00:17<00:04, 3.59it/s]\n 80%|████████ | 57/71 [00:17<00:03, 3.60it/s]\n 82%|████████▏ | 58/71 [00:18<00:03, 3.60it/s]\n 83%|████████▎ | 59/71 [00:18<00:03, 3.61it/s]\n 85%|████████▍ | 60/71 [00:18<00:03, 3.60it/s]\n 86%|████████▌ | 61/71 [00:18<00:02, 3.61it/s]\n 87%|████████▋ | 62/71 [00:19<00:02, 3.61it/s]\n 89%|████████▊ | 63/71 [00:19<00:02, 3.61it/s]\n 90%|█████████ | 64/71 [00:19<00:01, 3.61it/s]\n 92%|█████████▏| 65/71 [00:19<00:01, 3.61it/s]\n 93%|█████████▎| 66/71 [00:20<00:01, 3.61it/s]\n 94%|█████████▍| 67/71 [00:20<00:01, 3.61it/s]\n 96%|█████████▌| 68/71 [00:20<00:00, 3.61it/s]\n 97%|█████████▋| 69/71 [00:21<00:00, 3.61it/s]\n 99%|█████████▊| 70/71 [00:21<00:00, 3.61it/s]\n100%|██████████| 71/71 [00:22<00:00, 1.70it/s]\n100%|██████████| 71/71 [00:22<00:00, 3.13it/s]\npad talking image to original video\n 0%| | 0/564 [00:00<?, ?it/s]\n 0%| | 1/564 [00:00<01:55, 4.88it/s]\n 1%| | 3/564 [00:00<00:51, 10.87it/s]\n 1%| | 5/564 [00:00<00:40, 13.93it/s]\n 1%| | 7/564 [00:00<00:37, 14.98it/s]\n 2%|▏ | 9/564 [00:00<00:34, 16.26it/s]\n 2%|▏ | 11/564 [00:00<00:32, 17.09it/s]\n 2%|▏ | 13/564 [00:00<00:31, 17.70it/s]\n 3%|▎ | 15/564 [00:00<00:30, 18.18it/s]\n 3%|▎ | 17/564 [00:01<00:29, 18.37it/s]\n 3%|▎ | 19/564 [00:01<00:29, 18.59it/s]\n 4%|▎ | 21/564 [00:01<00:28, 18.79it/s]\n 4%|▍ | 23/564 [00:01<00:28, 18.89it/s]\n 4%|▍ | 25/564 [00:01<00:29, 18.56it/s]\n 5%|▍ | 27/564 [00:01<00:28, 18.83it/s]\n 5%|▌ | 29/564 [00:01<00:28, 19.02it/s]\n 5%|▌ | 31/564 [00:01<00:28, 18.98it/s]\n 6%|▌ | 33/564 [00:01<00:28, 18.95it/s]\n 6%|▌ | 35/564 [00:02<00:27, 19.06it/s]\n 7%|▋ | 37/564 [00:02<00:27, 18.99it/s]\n 7%|▋ | 39/564 [00:02<00:27, 19.02it/s]\n 7%|▋ | 41/564 [00:02<00:27, 18.99it/s]\n 8%|▊ | 43/564 [00:02<00:27, 18.97it/s]\n 8%|▊ | 45/564 [00:02<00:27, 18.88it/s]\n 8%|▊ | 47/564 [00:02<00:27, 18.77it/s]\n 9%|▊ | 49/564 [00:02<00:28, 18.29it/s]\n 9%|▉ | 51/564 [00:02<00:27, 18.42it/s]\n 9%|▉ | 53/564 [00:02<00:27, 18.37it/s]\n 10%|▉ | 55/564 [00:03<00:27, 18.43it/s]\n 10%|█ | 57/564 [00:03<00:27, 18.48it/s]\n 10%|█ | 59/564 [00:03<00:27, 18.43it/s]\n 11%|█ | 61/564 [00:03<00:27, 18.50it/s]\n 11%|█ | 63/564 [00:03<00:27, 17.96it/s]\n 12%|█▏ | 65/564 [00:03<00:27, 18.02it/s]\n 12%|█▏ | 67/564 [00:03<00:27, 18.21it/s]\n 12%|█▏ | 69/564 [00:03<00:27, 18.30it/s]\n 13%|█▎ | 71/564 [00:03<00:26, 18.45it/s]\n 13%|█▎ | 73/564 [00:04<00:26, 18.53it/s]\n 13%|█▎ | 75/564 [00:04<00:26, 18.69it/s]\n 14%|█▎ | 77/564 [00:04<00:25, 18.84it/s]\n 14%|█▍ | 79/564 [00:04<00:25, 18.97it/s]\n 14%|█▍ | 81/564 [00:04<00:25, 18.94it/s]\n 15%|█▍ | 83/564 [00:04<00:25, 18.81it/s]\n 15%|█▌ | 85/564 [00:04<00:25, 18.72it/s]\n 15%|█▌ | 87/564 [00:04<00:25, 18.72it/s]\n 16%|█▌ | 89/564 [00:04<00:25, 18.88it/s]\n 16%|█▌ | 91/564 [00:05<00:25, 18.74it/s]\n 16%|█▋ | 93/564 [00:05<00:25, 18.71it/s]\n 17%|█▋ | 95/564 [00:05<00:25, 18.69it/s]\n 17%|█▋ | 97/564 [00:05<00:24, 18.93it/s]\n 18%|█▊ | 99/564 [00:05<00:24, 18.96it/s]\n 18%|█▊ | 101/564 [00:05<00:24, 18.75it/s]\n 18%|█▊ | 103/564 [00:05<00:24, 18.58it/s]\n 19%|█▊ | 105/564 [00:05<00:24, 18.54it/s]\n 19%|█▉ | 107/564 [00:05<00:24, 18.32it/s]\n 19%|█▉ | 109/564 [00:05<00:24, 18.42it/s]\n 20%|█▉ | 111/564 [00:06<00:24, 18.47it/s]\n 20%|██ | 113/564 [00:06<00:24, 18.52it/s]\n 20%|██ | 115/564 [00:06<00:23, 18.76it/s]\n 21%|██ | 117/564 [00:06<00:23, 18.74it/s]\n 21%|██ | 119/564 [00:06<00:24, 17.96it/s]\n 21%|██▏ | 121/564 [00:06<00:24, 18.18it/s]\n 22%|██▏ | 123/564 [00:06<00:24, 18.35it/s]\n 22%|██▏ | 125/564 [00:06<00:23, 18.39it/s]\n 23%|██▎ | 127/564 [00:06<00:23, 18.45it/s]\n 23%|██▎ | 129/564 [00:07<00:23, 18.44it/s]\n 23%|██▎ | 131/564 [00:07<00:23, 18.43it/s]\n 24%|██▎ | 133/564 [00:07<00:23, 18.66it/s]\n 24%|██▍ | 135/564 [00:07<00:22, 18.67it/s]\n 24%|██▍ | 137/564 [00:07<00:23, 18.43it/s]\n 25%|██▍ | 139/564 [00:07<00:22, 18.56it/s]\n 25%|██▌ | 141/564 [00:07<00:22, 18.62it/s]\n 25%|██▌ | 143/564 [00:07<00:22, 18.66it/s]\n 26%|██▌ | 145/564 [00:07<00:22, 18.83it/s]\n 26%|██▌ | 147/564 [00:08<00:22, 18.81it/s]\n 26%|██▋ | 149/564 [00:08<00:22, 18.77it/s]\n 27%|██▋ | 151/564 [00:08<00:21, 18.85it/s]\n 27%|██▋ | 153/564 [00:08<00:21, 18.89it/s]\n 27%|██▋ | 155/564 [00:08<00:21, 18.79it/s]\n 28%|██▊ | 157/564 [00:08<00:21, 18.59it/s]\n 28%|██▊ | 159/564 [00:08<00:21, 18.67it/s]\n 29%|██▊ | 161/564 [00:08<00:21, 18.68it/s]\n 29%|██▉ | 163/564 [00:08<00:21, 18.66it/s]\n 29%|██▉ | 165/564 [00:08<00:21, 18.65it/s]\n 30%|██▉ | 167/564 [00:09<00:21, 18.66it/s]\n 30%|██▉ | 169/564 [00:09<00:21, 18.79it/s]\n 30%|███ | 171/564 [00:09<00:20, 18.91it/s]\n 31%|███ | 173/564 [00:09<00:20, 18.88it/s]\n 31%|███ | 175/564 [00:09<00:20, 18.77it/s]\n 31%|███▏ | 177/564 [00:09<00:20, 18.74it/s]\n 32%|███▏ | 179/564 [00:09<00:20, 18.71it/s]\n 32%|███▏ | 181/564 [00:09<00:20, 18.71it/s]\n 32%|███▏ | 183/564 [00:09<00:20, 18.78it/s]\n 33%|███▎ | 185/564 [00:10<00:20, 18.73it/s]\n 33%|███▎ | 187/564 [00:10<00:20, 18.77it/s]\n 34%|███▎ | 189/564 [00:10<00:19, 18.78it/s]\n 34%|███▍ | 191/564 [00:10<00:19, 18.70it/s]\n 34%|███▍ | 193/564 [00:10<00:19, 18.70it/s]\n 35%|███▍ | 195/564 [00:10<00:19, 18.83it/s]\n 35%|███▍ | 197/564 [00:10<00:19, 18.79it/s]\n 35%|███▌ | 199/564 [00:10<00:19, 18.73it/s]\n 36%|███▌ | 201/564 [00:10<00:19, 18.93it/s]\n 36%|███▌ | 203/564 [00:11<00:19, 18.93it/s]\n 36%|███▋ | 205/564 [00:11<00:18, 18.94it/s]\n 37%|███▋ | 207/564 [00:11<00:18, 18.97it/s]\n 37%|███▋ | 209/564 [00:11<00:18, 18.96it/s]\n 37%|███▋ | 211/564 [00:11<00:18, 18.88it/s]\n 38%|███▊ | 213/564 [00:11<00:18, 19.03it/s]\n 38%|███▊ | 215/564 [00:11<00:18, 18.92it/s]\n 38%|███▊ | 217/564 [00:11<00:18, 18.90it/s]\n 39%|███▉ | 219/564 [00:11<00:18, 18.89it/s]\n 39%|███▉ | 221/564 [00:11<00:18, 18.85it/s]\n 40%|███▉ | 223/564 [00:12<00:18, 18.85it/s]\n 40%|███▉ | 225/564 [00:12<00:18, 18.77it/s]\n 40%|████ | 227/564 [00:12<00:17, 18.80it/s]\n 41%|████ | 229/564 [00:12<00:17, 18.71it/s]\n 41%|████ | 231/564 [00:12<00:17, 18.68it/s]\n 41%|████▏ | 233/564 [00:12<00:17, 18.67it/s]\n 42%|████▏ | 235/564 [00:12<00:17, 18.60it/s]\n 42%|████▏ | 237/564 [00:12<00:17, 18.68it/s]\n 42%|████▏ | 239/564 [00:12<00:17, 18.80it/s]\n 43%|████▎ | 241/564 [00:13<00:17, 18.83it/s]\n 43%|████▎ | 243/564 [00:13<00:17, 18.77it/s]\n 43%|████▎ | 245/564 [00:13<00:16, 18.86it/s]\n 44%|████▍ | 247/564 [00:13<00:16, 19.02it/s]\n 44%|████▍ | 249/564 [00:13<00:16, 18.94it/s]\n 45%|████▍ | 251/564 [00:13<00:16, 18.62it/s]\n 45%|████▍ | 253/564 [00:13<00:16, 18.68it/s]\n 45%|████▌ | 255/564 [00:13<00:16, 18.81it/s]\n 46%|████▌ | 257/564 [00:13<00:16, 18.84it/s]\n 46%|████▌ | 259/564 [00:13<00:16, 18.84it/s]\n 46%|████▋ | 261/564 [00:14<00:16, 18.82it/s]\n 47%|████▋ | 263/564 [00:14<00:15, 18.92it/s]\n 47%|████▋ | 265/564 [00:14<00:15, 18.94it/s]\n 47%|████▋ | 267/564 [00:14<00:15, 18.91it/s]\n 48%|████▊ | 269/564 [00:14<00:16, 17.89it/s]\n 48%|████▊ | 271/564 [00:14<00:16, 18.17it/s]\n 48%|████▊ | 273/564 [00:14<00:15, 18.41it/s]\n 49%|████▉ | 275/564 [00:14<00:15, 18.56it/s]\n 49%|████▉ | 277/564 [00:14<00:15, 18.74it/s]\n 49%|████▉ | 279/564 [00:15<00:15, 18.79it/s]\n 50%|████▉ | 281/564 [00:15<00:15, 18.75it/s]\n 50%|█████ | 283/564 [00:15<00:14, 18.97it/s]\n 51%|█████ | 285/564 [00:15<00:14, 18.98it/s]\n 51%|█████ | 287/564 [00:15<00:14, 18.91it/s]\n 51%|█████ | 289/564 [00:15<00:14, 18.75it/s]\n 52%|█████▏ | 291/564 [00:15<00:14, 18.85it/s]\n 52%|█████▏ | 293/564 [00:15<00:14, 18.83it/s]\n 52%|█████▏ | 295/564 [00:15<00:14, 19.01it/s]\n 53%|█████▎ | 297/564 [00:16<00:14, 19.02it/s]\n 53%|█████▎ | 299/564 [00:16<00:14, 18.90it/s]\n 53%|█████▎ | 301/564 [00:16<00:13, 18.89it/s]\n 54%|█████▎ | 303/564 [00:16<00:13, 18.91it/s]\n 54%|█████▍ | 305/564 [00:16<00:13, 18.87it/s]\n 54%|█████▍ | 307/564 [00:16<00:13, 18.72it/s]\n 55%|█████▍ | 309/564 [00:16<00:13, 18.63it/s]\n 55%|█████▌ | 311/564 [00:16<00:13, 18.70it/s]\n 55%|█████▌ | 313/564 [00:16<00:13, 18.74it/s]\n 56%|█████▌ | 315/564 [00:16<00:13, 18.83it/s]\n 56%|█████▌ | 317/564 [00:17<00:13, 18.75it/s]\n 57%|█████▋ | 319/564 [00:17<00:13, 18.67it/s]\n 57%|█████▋ | 321/564 [00:17<00:13, 18.54it/s]\n 57%|█████▋ | 323/564 [00:17<00:12, 18.55it/s]\n 58%|█████▊ | 325/564 [00:17<00:13, 18.20it/s]\n 58%|█████▊ | 327/564 [00:17<00:12, 18.33it/s]\n 58%|█████▊ | 329/564 [00:17<00:12, 18.50it/s]\n 59%|█████▊ | 331/564 [00:17<00:12, 18.49it/s]\n 59%|█████▉ | 333/564 [00:17<00:12, 18.40it/s]\n 59%|█████▉ | 335/564 [00:18<00:12, 18.33it/s]\n 60%|█████▉ | 337/564 [00:18<00:12, 18.28it/s]\n 60%|██████ | 339/564 [00:18<00:12, 18.59it/s]\n 60%|██████ | 341/564 [00:18<00:11, 18.72it/s]\n 61%|██████ | 343/564 [00:18<00:11, 18.77it/s]\n 61%|██████ | 345/564 [00:18<00:11, 18.95it/s]\n 62%|██████▏ | 347/564 [00:18<00:11, 18.91it/s]\n 62%|██████▏ | 349/564 [00:18<00:11, 18.87it/s]\n 62%|██████▏ | 351/564 [00:18<00:11, 18.91it/s]\n 63%|██████▎ | 353/564 [00:19<00:11, 18.87it/s]\n 63%|██████▎ | 355/564 [00:19<00:11, 18.77it/s]\n 63%|██████▎ | 357/564 [00:19<00:10, 18.83it/s]\n 64%|██████▎ | 359/564 [00:19<00:10, 18.89it/s]\n 64%|██████▍ | 361/564 [00:19<00:10, 18.91it/s]\n 64%|██████▍ | 363/564 [00:19<00:10, 18.54it/s]\n 65%|██████▍ | 365/564 [00:19<00:10, 18.54it/s]\n 65%|██████▌ | 367/564 [00:19<00:10, 18.60it/s]\n 65%|██████▌ | 369/564 [00:19<00:10, 18.71it/s]\n 66%|██████▌ | 371/564 [00:19<00:10, 18.78it/s]\n 66%|██████▌ | 373/564 [00:20<00:10, 18.84it/s]\n 66%|██████▋ | 375/564 [00:20<00:10, 18.79it/s]\n 67%|██████▋ | 377/564 [00:20<00:09, 18.91it/s]\n 67%|██████▋ | 379/564 [00:20<00:09, 18.88it/s]\n 68%|██████▊ | 381/564 [00:20<00:09, 18.88it/s]\n 68%|██████▊ | 383/564 [00:20<00:09, 18.86it/s]\n 68%|██████▊ | 385/564 [00:20<00:09, 18.80it/s]\n 69%|██████▊ | 387/564 [00:20<00:09, 18.88it/s]\n 69%|██████▉ | 389/564 [00:20<00:09, 18.84it/s]\n 69%|██████▉ | 391/564 [00:21<00:09, 18.77it/s]\n 70%|██████▉ | 393/564 [00:21<00:09, 18.74it/s]\n 70%|███████ | 395/564 [00:21<00:08, 18.82it/s]\n 70%|███████ | 397/564 [00:21<00:08, 18.90it/s]\n 71%|███████ | 399/564 [00:21<00:08, 18.69it/s]\n 71%|███████ | 401/564 [00:21<00:08, 18.60it/s]\n 71%|███████▏ | 403/564 [00:21<00:08, 18.64it/s]\n 72%|███████▏ | 405/564 [00:21<00:08, 18.64it/s]\n 72%|███████▏ | 407/564 [00:21<00:08, 18.71it/s]\n 73%|███████▎ | 409/564 [00:22<00:08, 18.68it/s]\n 73%|███████▎ | 411/564 [00:22<00:08, 18.66it/s]\n 73%|███████▎ | 413/564 [00:22<00:08, 18.61it/s]\n 74%|███████▎ | 415/564 [00:22<00:07, 18.70it/s]\n 74%|███████▍ | 417/564 [00:22<00:07, 18.69it/s]\n 74%|███████▍ | 419/564 [00:22<00:07, 18.43it/s]\n 75%|███████▍ | 421/564 [00:22<00:07, 18.61it/s]\n 75%|███████▌ | 423/564 [00:22<00:07, 18.66it/s]\n 75%|███████▌ | 425/564 [00:22<00:07, 18.68it/s]\n 76%|███████▌ | 427/564 [00:22<00:07, 18.73it/s]\n 76%|███████▌ | 429/564 [00:23<00:07, 18.69it/s]\n 76%|███████▋ | 431/564 [00:23<00:07, 18.64it/s]\n 77%|███████▋ | 433/564 [00:23<00:06, 18.80it/s]\n 77%|███████▋ | 435/564 [00:23<00:06, 18.74it/s]\n 77%|███████▋ | 437/564 [00:23<00:06, 18.34it/s]\n 78%|███████▊ | 439/564 [00:23<00:06, 18.33it/s]\n 78%|███████▊ | 441/564 [00:23<00:06, 18.43it/s]\n 79%|███████▊ | 443/564 [00:23<00:06, 18.46it/s]\n 79%|███████▉ | 445/564 [00:23<00:06, 18.48it/s]\n 79%|███████▉ | 447/564 [00:24<00:06, 18.55it/s]\n 80%|███████▉ | 449/564 [00:24<00:06, 18.66it/s]\n 80%|███████▉ | 451/564 [00:24<00:06, 18.74it/s]\n 80%|████████ | 453/564 [00:24<00:05, 18.94it/s]\n 81%|████████ | 455/564 [00:24<00:05, 18.88it/s]\n 81%|████████ | 457/564 [00:24<00:05, 18.60it/s]\n 81%|████████▏ | 459/564 [00:24<00:05, 18.45it/s]\n 82%|████████▏ | 461/564 [00:24<00:05, 18.57it/s]\n 82%|████████▏ | 463/564 [00:24<00:05, 18.69it/s]\n 82%|████████▏ | 465/564 [00:25<00:05, 18.75it/s]\n 83%|████████▎ | 467/564 [00:25<00:05, 18.73it/s]\n 83%|████████▎ | 469/564 [00:25<00:05, 18.91it/s]\n 84%|████████▎ | 471/564 [00:25<00:04, 18.84it/s]\n 84%|████████▍ | 473/564 [00:25<00:04, 18.78it/s]\n 84%|████████▍ | 475/564 [00:25<00:04, 18.82it/s]\n 85%|████████▍ | 477/564 [00:25<00:04, 18.87it/s]\n 85%|████████▍ | 479/564 [00:25<00:04, 18.77it/s]\n 85%|████████▌ | 481/564 [00:25<00:04, 18.75it/s]\n 86%|████████▌ | 483/564 [00:25<00:04, 18.75it/s]\n 86%|████████▌ | 485/564 [00:26<00:04, 18.75it/s]\n 86%|████████▋ | 487/564 [00:26<00:04, 18.79it/s]\n 87%|████████▋ | 489/564 [00:26<00:03, 18.85it/s]\n 87%|████████▋ | 491/564 [00:26<00:03, 18.86it/s]\n 87%|████████▋ | 493/564 [00:26<00:03, 18.83it/s]\n 88%|████████▊ | 495/564 [00:26<00:03, 18.95it/s]\n 88%|████████▊ | 497/564 [00:26<00:03, 18.96it/s]\n 88%|████████▊ | 499/564 [00:26<00:03, 18.93it/s]\n 89%|████████▉ | 501/564 [00:26<00:03, 19.13it/s]\n 89%|████████▉ | 503/564 [00:27<00:03, 19.09it/s]\n 90%|████████▉ | 505/564 [00:27<00:03, 19.10it/s]\n 90%|████████▉ | 507/564 [00:27<00:02, 19.17it/s]\n 90%|█████████ | 509/564 [00:27<00:02, 19.14it/s]\n 91%|█████████ | 511/564 [00:27<00:02, 19.11it/s]\n 91%|█████████ | 513/564 [00:27<00:02, 19.10it/s]\n 91%|█████████▏| 515/564 [00:27<00:02, 19.01it/s]\n 92%|█████████▏| 517/564 [00:27<00:02, 19.01it/s]\n 92%|█████████▏| 519/564 [00:27<00:02, 18.99it/s]\n 92%|█████████▏| 521/564 [00:27<00:02, 18.92it/s]\n 93%|█████████▎| 523/564 [00:28<00:02, 18.92it/s]\n 93%|█████████▎| 525/564 [00:28<00:02, 18.98it/s]\n 93%|█████████▎| 527/564 [00:28<00:01, 19.13it/s]\n 94%|█████████▍| 529/564 [00:28<00:01, 18.89it/s]\n 94%|█████████▍| 531/564 [00:28<00:01, 18.97it/s]\n 95%|█████████▍| 533/564 [00:28<00:01, 18.98it/s]\n 95%|█████████▍| 535/564 [00:28<00:01, 18.90it/s]\n 95%|█████████▌| 537/564 [00:28<00:01, 18.86it/s]\n 96%|█████████▌| 539/564 [00:28<00:01, 18.80it/s]\n 96%|█████████▌| 541/564 [00:29<00:01, 18.81it/s]\n 96%|█████████▋| 543/564 [00:29<00:01, 18.85it/s]\n 97%|█████████▋| 545/564 [00:29<00:01, 18.93it/s]\n 97%|█████████▋| 547/564 [00:29<00:00, 19.02it/s]\n 97%|█████████▋| 549/564 [00:29<00:00, 18.95it/s]\n 98%|█████████▊| 551/564 [00:29<00:00, 18.62it/s]\n 98%|█████████▊| 553/564 [00:29<00:00, 18.75it/s]\n 98%|█████████▊| 555/564 [00:29<00:00, 18.77it/s]\n 99%|█████████▉| 557/564 [00:29<00:00, 18.88it/s]\n 99%|█████████▉| 559/564 [00:29<00:00, 18.91it/s]\n 99%|█████████▉| 561/564 [00:30<00:00, 18.95it/s]\n100%|█████████▉| 563/564 [00:30<00:00, 18.87it/s]\n100%|██████████| 564/564 [00:30<00:00, 18.65it/s]\nffmpeg -y -v warning -r 25.0 -f image2 -i /src/results/tmplxnmwn1zsun_tmp9xfjhifksun/%08d.png -vcodec libx264 -vf format=rgb24,scale=out_color_matrix=bt709,format=yuv420p -crf 18 temp.mp4\nffmpeg -y -v warning -i /tmp/tmp9xfjhifksun.wav -i temp.mp4 /src/results/tmplxnmwn1zsun_tmp9xfjhifksun.mp4\n[aist#0:0/pcm_s16le @ 0x55c2d0d10ec0] Guessed Channel Layout: mono\nresult is save to /src/results/tmplxnmwn1zsun_tmp9xfjhifksun.mp4", "metrics": { "predict_time": 144.266864, "total_time": 236.748296 }, "output": "https://replicate.delivery/pbxt/j8ZKhUHpxOZ4G9tfQbLhfLL56Q0c1krjKNvAMN3MeP7j462lA/tmplxnmwn1zsun_tmp9xfjhifksun.mp4", "started_at": "2024-06-05T08:40:35.287432Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/5d25am1qjsrgj0cfwy6v07mqg0", "cancel": "https://api.replicate.com/v1/predictions/5d25am1qjsrgj0cfwy6v07mqg0/cancel" }, "version": "5501004e78525e4bbd9fa20d1e75ad51fddce5a274bec07b9b16d685e34eeaf8" }
Generated inplease download ffmpeg-static and export to FFMPEG_PATH. For example: export FFMPEG_PATH=/musetalk/ffmpeg-4.4-amd64-static Loads checkpoint by local backend from path: ./models/dwpose/dw-ll_ucoco_384.pth cuda start Downloading: "https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth" to /root/.cache/torch/hub/checkpoints/s3fd-619a316812.pth 0%| | 0.00/85.7M [00:00<?, ?B/s] 0%| | 32.0k/85.7M [00:00<08:18, 180kB/s] 0%| | 80.0k/85.7M [00:00<06:21, 235kB/s] 0%| | 176k/85.7M [00:00<03:58, 376kB/s] 0%| | 384k/85.7M [00:00<02:09, 690kB/s] 1%| | 784k/85.7M [00:00<01:10, 1.26MB/s] 2%|▏ | 1.56M/85.7M [00:01<00:36, 2.40MB/s] 4%|▎ | 3.14M/85.7M [00:01<00:18, 4.60MB/s] 5%|▌ | 4.59M/85.7M [00:01<00:14, 5.76MB/s] 9%|▉ | 7.83M/85.7M [00:01<00:08, 9.84MB/s] 13%|█▎ | 11.0M/85.7M [00:01<00:06, 12.4MB/s] 17%|█▋ | 14.2M/85.7M [00:01<00:05, 14.4MB/s] 20%|██ | 17.5M/85.7M [00:02<00:04, 15.7MB/s] 24%|██▍ | 20.8M/85.7M [00:02<00:04, 16.8MB/s] 28%|██▊ | 24.2M/85.7M [00:02<00:03, 17.6MB/s] 32%|███▏ | 27.7M/85.7M [00:02<00:03, 18.3MB/s] 36%|███▋ | 31.1M/85.7M [00:02<00:03, 18.8MB/s] 40%|████ | 34.5M/85.7M [00:03<00:02, 19.2MB/s] 44%|████▍ | 38.1M/85.7M [00:03<00:02, 19.6MB/s] 49%|████▊ | 41.8M/85.7M [00:03<00:02, 20.1MB/s] 53%|█████▎ | 45.4M/85.7M [00:03<00:02, 20.5MB/s] 57%|█████▋ | 49.1M/85.7M [00:03<00:01, 23.6MB/s] 60%|██████ | 51.5M/85.7M [00:03<00:01, 23.3MB/s] 63%|██████▎ | 53.8M/85.7M [00:04<00:01, 19.9MB/s] 66%|██████▌ | 56.6M/85.7M [00:04<00:01, 20.1MB/s] 68%|██████▊ | 58.6M/85.7M [00:04<00:01, 15.9MB/s] 71%|███████ | 60.9M/85.7M [00:04<00:01, 15.1MB/s] 74%|███████▍ | 63.6M/85.7M [00:04<00:01, 15.3MB/s] 78%|███████▊ | 66.4M/85.7M [00:04<00:01, 15.5MB/s] 81%|████████ | 69.2M/85.7M [00:05<00:01, 15.7MB/s] 84%|████████▍ | 72.0M/85.7M [00:05<00:00, 15.8MB/s] 87%|████████▋ | 74.8M/85.7M [00:05<00:00, 15.9MB/s] 91%|█████████ | 77.6M/85.7M [00:05<00:00, 16.0MB/s] 94%|█████████▍| 80.5M/85.7M [00:05<00:00, 16.2MB/s] 97%|█████████▋| 83.3M/85.7M [00:06<00:00, 16.2MB/s] 100%|██████████| 85.7M/85.7M [00:06<00:00, 14.9MB/s] RUN: predict video in 25.0 FPS, audio idx in 50FPS extracting landmarks...time consuming reading images... 0%| | 0/550 [00:00<?, ?it/s] 3%|▎ | 18/550 [00:00<00:03, 174.06it/s] 7%|▋ | 36/550 [00:00<00:03, 168.18it/s] 10%|▉ | 53/550 [00:00<00:03, 162.51it/s] 13%|█▎ | 70/550 [00:00<00:02, 160.83it/s] 16%|█▌ | 87/550 [00:00<00:02, 158.52it/s] 19%|█▊ | 103/550 [00:00<00:02, 158.65it/s] 22%|██▏ | 119/550 [00:00<00:02, 158.15it/s] 25%|██▍ | 135/550 [00:00<00:02, 155.39it/s] 27%|██▋ | 151/550 [00:00<00:02, 153.15it/s] 30%|███ | 167/550 [00:01<00:02, 151.41it/s] 33%|███▎ | 183/550 [00:01<00:02, 150.10it/s] 36%|███▌ | 199/550 [00:01<00:02, 150.23it/s] 39%|███▉ | 215/550 [00:01<00:02, 152.64it/s] 42%|████▏ | 231/550 [00:01<00:02, 153.88it/s] 45%|████▍ | 247/550 [00:01<00:01, 154.31it/s] 48%|████▊ | 264/550 [00:01<00:01, 158.29it/s] 51%|█████ | 281/550 [00:01<00:01, 160.09it/s] 54%|█████▍ | 298/550 [00:01<00:01, 160.41it/s] 57%|█████▋ | 315/550 [00:02<00:01, 159.41it/s] 60%|██████ | 331/550 [00:02<00:01, 158.80it/s] 63%|██████▎ | 347/550 [00:02<00:01, 157.95it/s] 66%|██████▌ | 363/550 [00:02<00:01, 158.17it/s] 69%|██████▉ | 379/550 [00:02<00:01, 156.87it/s] 72%|███████▏ | 395/550 [00:02<00:00, 155.70it/s] 75%|███████▍ | 411/550 [00:02<00:00, 153.27it/s] 78%|███████▊ | 427/550 [00:02<00:00, 152.61it/s] 81%|████████ | 443/550 [00:02<00:00, 152.02it/s] 83%|████████▎ | 459/550 [00:02<00:00, 151.55it/s] 86%|████████▋ | 475/550 [00:03<00:00, 149.60it/s] 89%|████████▉ | 491/550 [00:03<00:00, 151.32it/s] 92%|█████████▏| 508/550 [00:03<00:00, 154.69it/s] 95%|█████████▌| 525/550 [00:03<00:00, 156.66it/s] 99%|█████████▊| 542/550 [00:03<00:00, 157.67it/s] 100%|██████████| 550/550 [00:03<00:00, 156.02it/s] get key_landmark and face bounding boxes with the default value 0%| | 0/550 [00:00<?, ?it/s] 0%| | 1/550 [00:00<05:41, 1.61it/s] 1%| | 3/550 [00:00<01:54, 4.79it/s] 1%| | 5/550 [00:00<01:11, 7.59it/s] 1%|▏ | 7/550 [00:00<00:55, 9.83it/s] 2%|▏ | 9/550 [00:01<00:46, 11.70it/s] 2%|▏ | 11/550 [00:01<00:41, 13.01it/s] 2%|▏ | 13/550 [00:01<00:37, 14.41it/s] 3%|▎ | 15/550 [00:01<00:35, 15.17it/s] 3%|▎ | 17/550 [00:01<00:33, 15.76it/s] 3%|▎ | 19/550 [00:01<00:33, 15.78it/s] 4%|▍ | 21/550 [00:01<00:33, 16.02it/s] 4%|▍ | 23/550 [00:01<00:32, 16.14it/s] 5%|▍ | 25/550 [00:02<00:31, 16.42it/s] 5%|▍ | 27/550 [00:02<00:31, 16.64it/s] 5%|▌ | 29/550 [00:02<00:31, 16.69it/s] 6%|▌ | 31/550 [00:02<00:31, 16.66it/s] 6%|▌ | 33/550 [00:02<00:31, 16.50it/s] 6%|▋ | 35/550 [00:02<00:30, 16.64it/s] 7%|▋ | 37/550 [00:02<00:30, 16.76it/s] 7%|▋ | 39/550 [00:02<00:30, 16.78it/s] 7%|▋ | 41/550 [00:03<00:30, 16.59it/s] 8%|▊ | 43/550 [00:03<00:31, 16.28it/s] 8%|▊ | 45/550 [00:03<00:31, 16.20it/s] 9%|▊ | 47/550 [00:03<00:31, 16.09it/s] 9%|▉ | 49/550 [00:03<00:32, 15.58it/s] 9%|▉ | 51/550 [00:03<00:31, 15.75it/s] 10%|▉ | 53/550 [00:03<00:31, 15.57it/s] 10%|█ | 55/550 [00:03<00:31, 15.69it/s] 10%|█ | 57/550 [00:04<00:30, 16.40it/s] 11%|█ | 59/550 [00:04<00:29, 16.47it/s] 11%|█ | 61/550 [00:04<00:30, 16.27it/s] 11%|█▏ | 63/550 [00:04<00:29, 16.41it/s] 12%|█▏ | 65/550 [00:04<00:29, 16.43it/s] 12%|█▏ | 67/550 [00:04<00:29, 16.11it/s] 13%|█▎ | 69/550 [00:04<00:29, 16.34it/s] 13%|█▎ | 71/550 [00:04<00:28, 16.52it/s] 13%|█▎ | 73/550 [00:04<00:29, 16.41it/s] 14%|█▎ | 75/550 [00:05<00:28, 16.46it/s] 14%|█▍ | 77/550 [00:05<00:28, 16.73it/s] 14%|█▍ | 79/550 [00:05<00:28, 16.72it/s] 15%|█▍ | 81/550 [00:05<00:27, 16.88it/s] 15%|█▌ | 83/550 [00:05<00:27, 16.94it/s] 15%|█▌ | 85/550 [00:05<00:28, 16.59it/s] 16%|█▌ | 87/550 [00:05<00:27, 16.91it/s] 16%|█▌ | 89/550 [00:05<00:27, 16.84it/s] 17%|█▋ | 91/550 [00:06<00:27, 16.93it/s] 17%|█▋ | 93/550 [00:06<00:26, 17.12it/s] 17%|█▋ | 95/550 [00:06<00:26, 17.23it/s] 18%|█▊ | 97/550 [00:06<00:26, 17.02it/s] 18%|█▊ | 99/550 [00:06<00:27, 16.21it/s] 18%|█▊ | 101/550 [00:06<00:27, 16.23it/s] 19%|█▊ | 103/550 [00:06<00:27, 16.32it/s] 19%|█▉ | 105/550 [00:06<00:26, 16.57it/s] 19%|█▉ | 107/550 [00:07<00:26, 16.55it/s] 20%|█▉ | 109/550 [00:07<00:26, 16.45it/s] 20%|██ | 111/550 [00:07<00:26, 16.47it/s] 21%|██ | 113/550 [00:07<00:26, 16.52it/s] 21%|██ | 115/550 [00:07<00:26, 16.47it/s] 21%|██▏ | 117/550 [00:07<00:26, 16.60it/s] 22%|██▏ | 119/550 [00:07<00:25, 16.66it/s] 22%|██▏ | 121/550 [00:07<00:25, 16.58it/s] 22%|██▏ | 123/550 [00:07<00:25, 16.89it/s] 23%|██▎ | 125/550 [00:08<00:24, 17.02it/s] 23%|██▎ | 127/550 [00:08<00:24, 17.23it/s] 23%|██▎ | 129/550 [00:08<00:24, 17.53it/s] 24%|██▍ | 131/550 [00:08<00:24, 17.40it/s] 24%|██▍ | 133/550 [00:08<00:23, 17.50it/s] 25%|██▍ | 135/550 [00:08<00:23, 17.66it/s] 25%|██▍ | 137/550 [00:08<00:23, 17.72it/s] 25%|██▌ | 139/550 [00:08<00:23, 17.42it/s] 26%|██▌ | 141/550 [00:09<00:24, 16.88it/s] 26%|██▌ | 143/550 [00:09<00:23, 16.98it/s] 26%|██▋ | 145/550 [00:09<00:23, 16.96it/s] 27%|██▋ | 147/550 [00:09<00:23, 17.13it/s] 27%|██▋ | 149/550 [00:09<00:23, 16.74it/s] 27%|██▋ | 151/550 [00:09<00:23, 17.07it/s] 28%|██▊ | 153/550 [00:09<00:23, 17.03it/s] 28%|██▊ | 155/550 [00:09<00:23, 16.98it/s] 29%|██▊ | 157/550 [00:09<00:23, 17.06it/s] 29%|██▉ | 159/550 [00:10<00:22, 17.34it/s] 29%|██▉ | 161/550 [00:10<00:22, 17.28it/s] 30%|██▉ | 163/550 [00:10<00:22, 17.34it/s] 30%|███ | 165/550 [00:10<00:22, 17.19it/s] 30%|███ | 167/550 [00:10<00:22, 17.13it/s] 31%|███ | 169/550 [00:10<00:22, 16.95it/s] 31%|███ | 171/550 [00:10<00:21, 17.28it/s] 31%|███▏ | 173/550 [00:10<00:22, 17.09it/s] 32%|███▏ | 175/550 [00:11<00:21, 17.09it/s] 32%|███▏ | 177/550 [00:11<00:21, 16.99it/s] 33%|███▎ | 179/550 [00:11<00:21, 17.01it/s] 33%|███▎ | 181/550 [00:11<00:21, 17.25it/s] 33%|███▎ | 183/550 [00:11<00:21, 17.14it/s] 34%|███▎ | 185/550 [00:11<00:21, 16.82it/s] 34%|███▍ | 187/550 [00:11<00:21, 16.87it/s] 34%|███▍ | 189/550 [00:11<00:21, 16.86it/s] 35%|███▍ | 191/550 [00:11<00:21, 17.03it/s] 35%|███▌ | 193/550 [00:12<00:21, 16.89it/s] 35%|███▌ | 195/550 [00:12<00:21, 16.76it/s] 36%|███▌ | 197/550 [00:12<00:21, 16.59it/s] 36%|███▌ | 199/550 [00:12<00:21, 16.69it/s] 37%|███▋ | 201/550 [00:12<00:20, 16.90it/s] 37%|███▋ | 203/550 [00:12<00:20, 16.93it/s] 37%|███▋ | 205/550 [00:12<00:20, 16.75it/s] 38%|███▊ | 207/550 [00:12<00:20, 16.60it/s] 38%|███▊ | 209/550 [00:13<00:20, 16.38it/s] 38%|███▊ | 211/550 [00:13<00:21, 16.11it/s] 39%|███▊ | 213/550 [00:13<00:20, 16.08it/s] 39%|███▉ | 215/550 [00:13<00:20, 16.11it/s] 39%|███▉ | 217/550 [00:13<00:20, 16.05it/s] 40%|███▉ | 219/550 [00:13<00:20, 16.53it/s] 40%|████ | 221/550 [00:13<00:19, 16.64it/s] 41%|████ | 223/550 [00:13<00:19, 16.66it/s] 41%|████ | 225/550 [00:14<00:19, 16.71it/s] 41%|████▏ | 227/550 [00:14<00:19, 16.98it/s] 42%|████▏ | 229/550 [00:14<00:19, 16.80it/s] 42%|████▏ | 231/550 [00:14<00:18, 16.98it/s] 42%|████▏ | 233/550 [00:14<00:18, 17.23it/s] 43%|████▎ | 235/550 [00:14<00:18, 17.37it/s] 43%|████▎ | 237/550 [00:14<00:17, 17.49it/s] 43%|████▎ | 239/550 [00:14<00:17, 17.38it/s] 44%|████▍ | 241/550 [00:14<00:17, 17.18it/s] 44%|████▍ | 243/550 [00:15<00:17, 17.16it/s] 45%|████▍ | 245/550 [00:15<00:17, 17.23it/s] 45%|████▍ | 247/550 [00:15<00:17, 17.26it/s] 45%|████▌ | 249/550 [00:15<00:17, 17.11it/s] 46%|████▌ | 251/550 [00:15<00:17, 17.22it/s] 46%|████▌ | 253/550 [00:15<00:17, 17.09it/s] 46%|████▋ | 255/550 [00:15<00:17, 16.62it/s] 47%|████▋ | 257/550 [00:15<00:17, 16.76it/s] 47%|████▋ | 259/550 [00:16<00:17, 16.69it/s] 47%|████▋ | 261/550 [00:16<00:17, 16.93it/s] 48%|████▊ | 263/550 [00:16<00:16, 17.01it/s] 48%|████▊ | 265/550 [00:16<00:16, 17.15it/s] 49%|████▊ | 267/550 [00:16<00:16, 17.25it/s] 49%|████▉ | 269/550 [00:16<00:16, 16.82it/s] 49%|████▉ | 271/550 [00:16<00:16, 17.22it/s] 50%|████▉ | 273/550 [00:16<00:16, 17.13it/s] 50%|█████ | 275/550 [00:16<00:16, 17.02it/s] 50%|█████ | 277/550 [00:17<00:15, 17.12it/s] 51%|█████ | 279/550 [00:17<00:15, 17.12it/s] 51%|█████ | 281/550 [00:17<00:15, 17.05it/s] 51%|█████▏ | 283/550 [00:17<00:15, 16.91it/s] 52%|█████▏ | 285/550 [00:17<00:15, 16.79it/s] 52%|█████▏ | 287/550 [00:17<00:15, 16.95it/s] 53%|█████▎ | 289/550 [00:17<00:15, 16.97it/s] 53%|█████▎ | 291/550 [00:17<00:15, 16.94it/s] 53%|█████▎ | 293/550 [00:17<00:15, 16.94it/s] 54%|█████▎ | 295/550 [00:18<00:14, 17.17it/s] 54%|█████▍ | 297/550 [00:18<00:14, 17.21it/s] 54%|█████▍ | 299/550 [00:18<00:14, 17.11it/s] 55%|█████▍ | 301/550 [00:18<00:14, 17.07it/s] 55%|█████▌ | 303/550 [00:18<00:14, 16.66it/s] 55%|█████▌ | 305/550 [00:18<00:14, 16.72it/s] 56%|█████▌ | 307/550 [00:18<00:14, 16.99it/s] 56%|█████▌ | 309/550 [00:18<00:14, 17.19it/s] 57%|█████▋ | 311/550 [00:19<00:13, 17.41it/s] 57%|█████▋ | 313/550 [00:19<00:13, 17.49it/s] 57%|█████▋ | 315/550 [00:19<00:13, 17.67it/s] 58%|█████▊ | 317/550 [00:19<00:13, 17.49it/s] 58%|█████▊ | 319/550 [00:19<00:13, 16.79it/s] 58%|█████▊ | 321/550 [00:19<00:13, 16.94it/s] 59%|█████▊ | 323/550 [00:19<00:13, 17.03it/s] 59%|█████▉ | 325/550 [00:19<00:13, 16.82it/s] 59%|█████▉ | 327/550 [00:19<00:13, 16.73it/s] 60%|█████▉ | 329/550 [00:20<00:12, 17.09it/s] 60%|██████ | 331/550 [00:20<00:13, 16.81it/s] 61%|██████ | 333/550 [00:20<00:12, 16.75it/s] 61%|██████ | 335/550 [00:20<00:13, 16.45it/s] 61%|██████▏ | 337/550 [00:20<00:12, 16.56it/s] 62%|██████▏ | 339/550 [00:20<00:12, 16.48it/s] 62%|██████▏ | 341/550 [00:20<00:12, 16.19it/s] 62%|██████▏ | 343/550 [00:20<00:13, 15.91it/s] 63%|██████▎ | 345/550 [00:21<00:12, 16.46it/s] 63%|██████▎ | 347/550 [00:21<00:12, 16.69it/s] 63%|██████▎ | 349/550 [00:21<00:11, 16.89it/s] 64%|██████▍ | 351/550 [00:21<00:11, 17.10it/s] 64%|██████▍ | 353/550 [00:21<00:11, 17.34it/s] 65%|██████▍ | 355/550 [00:21<00:11, 17.63it/s] 65%|██████▍ | 357/550 [00:21<00:11, 17.49it/s] 65%|██████▌ | 359/550 [00:21<00:10, 17.58it/s] 66%|██████▌ | 361/550 [00:22<00:11, 17.11it/s] 66%|██████▌ | 363/550 [00:22<00:10, 17.30it/s] 66%|██████▋ | 365/550 [00:22<00:10, 17.43it/s] 67%|██████▋ | 367/550 [00:22<00:10, 17.32it/s] 67%|██████▋ | 369/550 [00:22<00:10, 17.19it/s] 67%|██████▋ | 371/550 [00:22<00:10, 16.99it/s] 68%|██████▊ | 373/550 [00:22<00:10, 16.98it/s] 68%|██████▊ | 375/550 [00:22<00:10, 16.95it/s] 69%|██████▊ | 377/550 [00:22<00:10, 16.67it/s] 69%|██████▉ | 379/550 [00:23<00:10, 17.06it/s] 69%|██████▉ | 381/550 [00:23<00:09, 17.27it/s] 70%|██████▉ | 383/550 [00:23<00:09, 17.03it/s] 70%|███████ | 385/550 [00:23<00:09, 16.97it/s] 70%|███████ | 387/550 [00:23<00:09, 16.81it/s] 71%|███████ | 389/550 [00:23<00:09, 16.80it/s] 71%|███████ | 391/550 [00:23<00:09, 16.65it/s] 71%|███████▏ | 393/550 [00:23<00:09, 16.90it/s] 72%|███████▏ | 395/550 [00:24<00:09, 17.00it/s] 72%|███████▏ | 397/550 [00:24<00:08, 17.22it/s] 73%|███████▎ | 399/550 [00:24<00:08, 17.25it/s] 73%|███████▎ | 401/550 [00:24<00:08, 16.94it/s] 73%|███████▎ | 403/550 [00:24<00:08, 16.86it/s] 74%|███████▎ | 405/550 [00:24<00:08, 17.08it/s] 74%|███████▍ | 407/550 [00:24<00:08, 17.22it/s] 74%|███████▍ | 409/550 [00:24<00:08, 17.32it/s] 75%|███████▍ | 411/550 [00:24<00:07, 17.38it/s] 75%|███████▌ | 413/550 [00:25<00:07, 17.29it/s] 75%|███████▌ | 415/550 [00:25<00:07, 17.70it/s] 76%|███████▌ | 417/550 [00:25<00:07, 17.79it/s] 76%|███████▌ | 419/550 [00:25<00:07, 17.67it/s] 77%|███████▋ | 421/550 [00:25<00:07, 17.73it/s] 77%|███████▋ | 423/550 [00:25<00:07, 17.77it/s] 77%|███████▋ | 425/550 [00:25<00:07, 17.55it/s] 78%|███████▊ | 427/550 [00:25<00:06, 17.70it/s] 78%|███████▊ | 429/550 [00:25<00:06, 17.62it/s] 78%|███████▊ | 431/550 [00:26<00:06, 17.88it/s] 79%|███████▊ | 433/550 [00:26<00:06, 18.13it/s] 79%|███████▉ | 435/550 [00:26<00:06, 18.17it/s] 79%|███████▉ | 437/550 [00:26<00:06, 18.19it/s] 80%|███████▉ | 439/550 [00:26<00:06, 17.96it/s] 80%|████████ | 441/550 [00:26<00:06, 18.12it/s] 81%|████████ | 443/550 [00:26<00:06, 17.68it/s] 81%|████████ | 445/550 [00:26<00:05, 17.69it/s] 81%|████████▏ | 447/550 [00:26<00:05, 17.87it/s] 82%|████████▏ | 449/550 [00:27<00:05, 17.75it/s] 82%|████████▏ | 451/550 [00:27<00:05, 17.47it/s] 82%|████████▏ | 453/550 [00:27<00:05, 17.48it/s] 83%|████████▎ | 455/550 [00:27<00:05, 17.51it/s] 83%|████████▎ | 457/550 [00:27<00:05, 17.75it/s] 83%|████████▎ | 459/550 [00:27<00:05, 17.68it/s] 84%|████████▍ | 461/550 [00:27<00:05, 17.66it/s] 84%|████████▍ | 463/550 [00:27<00:04, 17.73it/s] 85%|████████▍ | 465/550 [00:27<00:04, 17.65it/s] 85%|████████▍ | 467/550 [00:28<00:04, 17.23it/s] 85%|████████▌ | 469/550 [00:28<00:04, 17.32it/s] 86%|████████▌ | 471/550 [00:28<00:04, 17.63it/s] 86%|████████▌ | 473/550 [00:28<00:04, 17.60it/s] 86%|████████▋ | 475/550 [00:28<00:04, 17.11it/s] 87%|████████▋ | 477/550 [00:28<00:04, 16.55it/s] 87%|████████▋ | 479/550 [00:28<00:04, 16.67it/s] 87%|████████▋ | 481/550 [00:28<00:04, 16.70it/s] 88%|████████▊ | 483/550 [00:29<00:03, 16.78it/s] 88%|████████▊ | 485/550 [00:29<00:03, 16.90it/s] 89%|████████▊ | 487/550 [00:29<00:03, 17.05it/s] 89%|████████▉ | 489/550 [00:29<00:03, 17.18it/s] 89%|████████▉ | 491/550 [00:29<00:03, 17.34it/s] 90%|████████▉ | 493/550 [00:29<00:03, 17.63it/s] 90%|█████████ | 495/550 [00:29<00:03, 17.49it/s] 90%|█████████ | 497/550 [00:29<00:03, 17.39it/s] 91%|█████████ | 499/550 [00:29<00:02, 17.13it/s] 91%|█████████ | 501/550 [00:30<00:02, 16.85it/s] 91%|█████████▏| 503/550 [00:30<00:02, 16.73it/s] 92%|█████████▏| 505/550 [00:30<00:02, 16.76it/s] 92%|█████████▏| 507/550 [00:30<00:02, 17.15it/s] 93%|█████████▎| 509/550 [00:30<00:02, 17.16it/s] 93%|█████████▎| 511/550 [00:30<00:02, 17.47it/s] 93%|█████████▎| 513/550 [00:30<00:02, 17.32it/s] 94%|█████████▎| 515/550 [00:30<00:02, 16.90it/s] 94%|█████████▍| 517/550 [00:31<00:01, 16.98it/s] 94%|█████████▍| 519/550 [00:31<00:01, 17.06it/s] 95%|█████████▍| 521/550 [00:31<00:01, 16.94it/s] 95%|█████████▌| 523/550 [00:31<00:01, 16.73it/s] 95%|█████████▌| 525/550 [00:31<00:01, 16.93it/s] 96%|█████████▌| 527/550 [00:31<00:01, 17.17it/s] 96%|█████████▌| 529/550 [00:31<00:01, 16.94it/s] 97%|█████████▋| 531/550 [00:31<00:01, 16.79it/s] 97%|█████████▋| 533/550 [00:31<00:01, 16.71it/s] 97%|█████████▋| 535/550 [00:32<00:00, 16.53it/s] 98%|█████████▊| 537/550 [00:32<00:00, 16.61it/s] 98%|█████████▊| 539/550 [00:32<00:00, 16.65it/s] 98%|█████████▊| 541/550 [00:32<00:00, 16.42it/s] 99%|█████████▊| 543/550 [00:32<00:00, 15.93it/s] 99%|█████████▉| 545/550 [00:32<00:00, 16.15it/s] 99%|█████████▉| 547/550 [00:32<00:00, 16.41it/s] 100%|█████████▉| 549/550 [00:32<00:00, 16.41it/s] 100%|██████████| 550/550 [00:33<00:00, 16.66it/s] ********************************************bbox_shift parameter adjustment********************************************************** Total frame:「550」 Manually adjust range : [ -9~9 ] , the current value: 0 ************************************************************************************************************************************* start inference 0%| | 0/71 [00:00<?, ?it/s] 1%|▏ | 1/71 [00:02<02:23, 2.05s/it] 3%|▎ | 2/71 [00:02<01:09, 1.01s/it] 4%|▍ | 3/71 [00:02<00:46, 1.48it/s] 6%|▌ | 4/71 [00:02<00:34, 1.93it/s] 7%|▋ | 5/71 [00:03<00:28, 2.29it/s] 8%|▊ | 6/71 [00:03<00:24, 2.60it/s] 10%|▉ | 7/71 [00:03<00:22, 2.85it/s] 11%|█▏ | 8/71 [00:04<00:20, 3.04it/s] 13%|█▎ | 9/71 [00:04<00:19, 3.19it/s] 14%|█▍ | 10/71 [00:04<00:18, 3.29it/s] 15%|█▌ | 11/71 [00:04<00:17, 3.38it/s] 17%|█▋ | 12/71 [00:05<00:17, 3.44it/s] 18%|█▊ | 13/71 [00:05<00:16, 3.48it/s] 20%|█▉ | 14/71 [00:05<00:16, 3.52it/s] 21%|██ | 15/71 [00:05<00:15, 3.53it/s] 23%|██▎ | 16/71 [00:06<00:15, 3.52it/s] 24%|██▍ | 17/71 [00:06<00:15, 3.55it/s] 25%|██▌ | 18/71 [00:06<00:14, 3.56it/s] 27%|██▋ | 19/71 [00:07<00:14, 3.56it/s] 28%|██▊ | 20/71 [00:07<00:14, 3.56it/s] 30%|██▉ | 21/71 [00:07<00:14, 3.56it/s] 31%|███ | 22/71 [00:07<00:13, 3.58it/s] 32%|███▏ | 23/71 [00:08<00:13, 3.59it/s] 34%|███▍ | 24/71 [00:08<00:13, 3.57it/s] 35%|███▌ | 25/71 [00:08<00:12, 3.57it/s] 37%|███▋ | 26/71 [00:09<00:12, 3.56it/s] 38%|███▊ | 27/71 [00:09<00:12, 3.56it/s] 39%|███▉ | 28/71 [00:09<00:12, 3.55it/s] 41%|████ | 29/71 [00:09<00:11, 3.56it/s] 42%|████▏ | 30/71 [00:10<00:11, 3.55it/s] 44%|████▎ | 31/71 [00:10<00:11, 3.57it/s] 45%|████▌ | 32/71 [00:10<00:10, 3.56it/s] 46%|████▋ | 33/71 [00:11<00:10, 3.56it/s] 48%|████▊ | 34/71 [00:11<00:10, 3.55it/s] 49%|████▉ | 35/71 [00:11<00:10, 3.55it/s] 51%|█████ | 36/71 [00:11<00:09, 3.56it/s] 52%|█████▏ | 37/71 [00:12<00:09, 3.57it/s] 54%|█████▎ | 38/71 [00:12<00:09, 3.56it/s] 55%|█████▍ | 39/71 [00:12<00:08, 3.56it/s] 56%|█████▋ | 40/71 [00:12<00:08, 3.57it/s] 58%|█████▊ | 41/71 [00:13<00:08, 3.56it/s] 59%|█████▉ | 42/71 [00:13<00:08, 3.58it/s] 61%|██████ | 43/71 [00:13<00:07, 3.58it/s] 62%|██████▏ | 44/71 [00:14<00:07, 3.56it/s] 63%|██████▎ | 45/71 [00:14<00:07, 3.56it/s] 65%|██████▍ | 46/71 [00:14<00:07, 3.55it/s] 66%|██████▌ | 47/71 [00:14<00:06, 3.55it/s] 68%|██████▊ | 48/71 [00:15<00:06, 3.54it/s] 69%|██████▉ | 49/71 [00:15<00:06, 3.57it/s] 70%|███████ | 50/71 [00:15<00:05, 3.57it/s] 72%|███████▏ | 51/71 [00:16<00:05, 3.58it/s] 73%|███████▎ | 52/71 [00:16<00:05, 3.58it/s] 75%|███████▍ | 53/71 [00:16<00:05, 3.60it/s] 76%|███████▌ | 54/71 [00:16<00:04, 3.60it/s] 77%|███████▋ | 55/71 [00:17<00:04, 3.60it/s] 79%|███████▉ | 56/71 [00:17<00:04, 3.59it/s] 80%|████████ | 57/71 [00:17<00:03, 3.60it/s] 82%|████████▏ | 58/71 [00:18<00:03, 3.60it/s] 83%|████████▎ | 59/71 [00:18<00:03, 3.61it/s] 85%|████████▍ | 60/71 [00:18<00:03, 3.60it/s] 86%|████████▌ | 61/71 [00:18<00:02, 3.61it/s] 87%|████████▋ | 62/71 [00:19<00:02, 3.61it/s] 89%|████████▊ | 63/71 [00:19<00:02, 3.61it/s] 90%|█████████ | 64/71 [00:19<00:01, 3.61it/s] 92%|█████████▏| 65/71 [00:19<00:01, 3.61it/s] 93%|█████████▎| 66/71 [00:20<00:01, 3.61it/s] 94%|█████████▍| 67/71 [00:20<00:01, 3.61it/s] 96%|█████████▌| 68/71 [00:20<00:00, 3.61it/s] 97%|█████████▋| 69/71 [00:21<00:00, 3.61it/s] 99%|█████████▊| 70/71 [00:21<00:00, 3.61it/s] 100%|██████████| 71/71 [00:22<00:00, 1.70it/s] 100%|██████████| 71/71 [00:22<00:00, 3.13it/s] pad talking image to original video 0%| | 0/564 [00:00<?, ?it/s] 0%| | 1/564 [00:00<01:55, 4.88it/s] 1%| | 3/564 [00:00<00:51, 10.87it/s] 1%| | 5/564 [00:00<00:40, 13.93it/s] 1%| | 7/564 [00:00<00:37, 14.98it/s] 2%|▏ | 9/564 [00:00<00:34, 16.26it/s] 2%|▏ | 11/564 [00:00<00:32, 17.09it/s] 2%|▏ | 13/564 [00:00<00:31, 17.70it/s] 3%|▎ | 15/564 [00:00<00:30, 18.18it/s] 3%|▎ | 17/564 [00:01<00:29, 18.37it/s] 3%|▎ | 19/564 [00:01<00:29, 18.59it/s] 4%|▎ | 21/564 [00:01<00:28, 18.79it/s] 4%|▍ | 23/564 [00:01<00:28, 18.89it/s] 4%|▍ | 25/564 [00:01<00:29, 18.56it/s] 5%|▍ | 27/564 [00:01<00:28, 18.83it/s] 5%|▌ | 29/564 [00:01<00:28, 19.02it/s] 5%|▌ | 31/564 [00:01<00:28, 18.98it/s] 6%|▌ | 33/564 [00:01<00:28, 18.95it/s] 6%|▌ | 35/564 [00:02<00:27, 19.06it/s] 7%|▋ | 37/564 [00:02<00:27, 18.99it/s] 7%|▋ | 39/564 [00:02<00:27, 19.02it/s] 7%|▋ | 41/564 [00:02<00:27, 18.99it/s] 8%|▊ | 43/564 [00:02<00:27, 18.97it/s] 8%|▊ | 45/564 [00:02<00:27, 18.88it/s] 8%|▊ | 47/564 [00:02<00:27, 18.77it/s] 9%|▊ | 49/564 [00:02<00:28, 18.29it/s] 9%|▉ | 51/564 [00:02<00:27, 18.42it/s] 9%|▉ | 53/564 [00:02<00:27, 18.37it/s] 10%|▉ | 55/564 [00:03<00:27, 18.43it/s] 10%|█ | 57/564 [00:03<00:27, 18.48it/s] 10%|█ | 59/564 [00:03<00:27, 18.43it/s] 11%|█ | 61/564 [00:03<00:27, 18.50it/s] 11%|█ | 63/564 [00:03<00:27, 17.96it/s] 12%|█▏ | 65/564 [00:03<00:27, 18.02it/s] 12%|█▏ | 67/564 [00:03<00:27, 18.21it/s] 12%|█▏ | 69/564 [00:03<00:27, 18.30it/s] 13%|█▎ | 71/564 [00:03<00:26, 18.45it/s] 13%|█▎ | 73/564 [00:04<00:26, 18.53it/s] 13%|█▎ | 75/564 [00:04<00:26, 18.69it/s] 14%|█▎ | 77/564 [00:04<00:25, 18.84it/s] 14%|█▍ | 79/564 [00:04<00:25, 18.97it/s] 14%|█▍ | 81/564 [00:04<00:25, 18.94it/s] 15%|█▍ | 83/564 [00:04<00:25, 18.81it/s] 15%|█▌ | 85/564 [00:04<00:25, 18.72it/s] 15%|█▌ | 87/564 [00:04<00:25, 18.72it/s] 16%|█▌ | 89/564 [00:04<00:25, 18.88it/s] 16%|█▌ | 91/564 [00:05<00:25, 18.74it/s] 16%|█▋ | 93/564 [00:05<00:25, 18.71it/s] 17%|█▋ | 95/564 [00:05<00:25, 18.69it/s] 17%|█▋ | 97/564 [00:05<00:24, 18.93it/s] 18%|█▊ | 99/564 [00:05<00:24, 18.96it/s] 18%|█▊ | 101/564 [00:05<00:24, 18.75it/s] 18%|█▊ | 103/564 [00:05<00:24, 18.58it/s] 19%|█▊ | 105/564 [00:05<00:24, 18.54it/s] 19%|█▉ | 107/564 [00:05<00:24, 18.32it/s] 19%|█▉ | 109/564 [00:05<00:24, 18.42it/s] 20%|█▉ | 111/564 [00:06<00:24, 18.47it/s] 20%|██ | 113/564 [00:06<00:24, 18.52it/s] 20%|██ | 115/564 [00:06<00:23, 18.76it/s] 21%|██ | 117/564 [00:06<00:23, 18.74it/s] 21%|██ | 119/564 [00:06<00:24, 17.96it/s] 21%|██▏ | 121/564 [00:06<00:24, 18.18it/s] 22%|██▏ | 123/564 [00:06<00:24, 18.35it/s] 22%|██▏ | 125/564 [00:06<00:23, 18.39it/s] 23%|██▎ | 127/564 [00:06<00:23, 18.45it/s] 23%|██▎ | 129/564 [00:07<00:23, 18.44it/s] 23%|██▎ | 131/564 [00:07<00:23, 18.43it/s] 24%|██▎ | 133/564 [00:07<00:23, 18.66it/s] 24%|██▍ | 135/564 [00:07<00:22, 18.67it/s] 24%|██▍ | 137/564 [00:07<00:23, 18.43it/s] 25%|██▍ | 139/564 [00:07<00:22, 18.56it/s] 25%|██▌ | 141/564 [00:07<00:22, 18.62it/s] 25%|██▌ | 143/564 [00:07<00:22, 18.66it/s] 26%|██▌ | 145/564 [00:07<00:22, 18.83it/s] 26%|██▌ | 147/564 [00:08<00:22, 18.81it/s] 26%|██▋ | 149/564 [00:08<00:22, 18.77it/s] 27%|██▋ | 151/564 [00:08<00:21, 18.85it/s] 27%|██▋ | 153/564 [00:08<00:21, 18.89it/s] 27%|██▋ | 155/564 [00:08<00:21, 18.79it/s] 28%|██▊ | 157/564 [00:08<00:21, 18.59it/s] 28%|██▊ | 159/564 [00:08<00:21, 18.67it/s] 29%|██▊ | 161/564 [00:08<00:21, 18.68it/s] 29%|██▉ | 163/564 [00:08<00:21, 18.66it/s] 29%|██▉ | 165/564 [00:08<00:21, 18.65it/s] 30%|██▉ | 167/564 [00:09<00:21, 18.66it/s] 30%|██▉ | 169/564 [00:09<00:21, 18.79it/s] 30%|███ | 171/564 [00:09<00:20, 18.91it/s] 31%|███ | 173/564 [00:09<00:20, 18.88it/s] 31%|███ | 175/564 [00:09<00:20, 18.77it/s] 31%|███▏ | 177/564 [00:09<00:20, 18.74it/s] 32%|███▏ | 179/564 [00:09<00:20, 18.71it/s] 32%|███▏ | 181/564 [00:09<00:20, 18.71it/s] 32%|███▏ | 183/564 [00:09<00:20, 18.78it/s] 33%|███▎ | 185/564 [00:10<00:20, 18.73it/s] 33%|███▎ | 187/564 [00:10<00:20, 18.77it/s] 34%|███▎ | 189/564 [00:10<00:19, 18.78it/s] 34%|███▍ | 191/564 [00:10<00:19, 18.70it/s] 34%|███▍ | 193/564 [00:10<00:19, 18.70it/s] 35%|███▍ | 195/564 [00:10<00:19, 18.83it/s] 35%|███▍ | 197/564 [00:10<00:19, 18.79it/s] 35%|███▌ | 199/564 [00:10<00:19, 18.73it/s] 36%|███▌ | 201/564 [00:10<00:19, 18.93it/s] 36%|███▌ | 203/564 [00:11<00:19, 18.93it/s] 36%|███▋ | 205/564 [00:11<00:18, 18.94it/s] 37%|███▋ | 207/564 [00:11<00:18, 18.97it/s] 37%|███▋ | 209/564 [00:11<00:18, 18.96it/s] 37%|███▋ | 211/564 [00:11<00:18, 18.88it/s] 38%|███▊ | 213/564 [00:11<00:18, 19.03it/s] 38%|███▊ | 215/564 [00:11<00:18, 18.92it/s] 38%|███▊ | 217/564 [00:11<00:18, 18.90it/s] 39%|███▉ | 219/564 [00:11<00:18, 18.89it/s] 39%|███▉ | 221/564 [00:11<00:18, 18.85it/s] 40%|███▉ | 223/564 [00:12<00:18, 18.85it/s] 40%|███▉ | 225/564 [00:12<00:18, 18.77it/s] 40%|████ | 227/564 [00:12<00:17, 18.80it/s] 41%|████ | 229/564 [00:12<00:17, 18.71it/s] 41%|████ | 231/564 [00:12<00:17, 18.68it/s] 41%|████▏ | 233/564 [00:12<00:17, 18.67it/s] 42%|████▏ | 235/564 [00:12<00:17, 18.60it/s] 42%|████▏ | 237/564 [00:12<00:17, 18.68it/s] 42%|████▏ | 239/564 [00:12<00:17, 18.80it/s] 43%|████▎ | 241/564 [00:13<00:17, 18.83it/s] 43%|████▎ | 243/564 [00:13<00:17, 18.77it/s] 43%|████▎ | 245/564 [00:13<00:16, 18.86it/s] 44%|████▍ | 247/564 [00:13<00:16, 19.02it/s] 44%|████▍ | 249/564 [00:13<00:16, 18.94it/s] 45%|████▍ | 251/564 [00:13<00:16, 18.62it/s] 45%|████▍ | 253/564 [00:13<00:16, 18.68it/s] 45%|████▌ | 255/564 [00:13<00:16, 18.81it/s] 46%|████▌ | 257/564 [00:13<00:16, 18.84it/s] 46%|████▌ | 259/564 [00:13<00:16, 18.84it/s] 46%|████▋ | 261/564 [00:14<00:16, 18.82it/s] 47%|████▋ | 263/564 [00:14<00:15, 18.92it/s] 47%|████▋ | 265/564 [00:14<00:15, 18.94it/s] 47%|████▋ | 267/564 [00:14<00:15, 18.91it/s] 48%|████▊ | 269/564 [00:14<00:16, 17.89it/s] 48%|████▊ | 271/564 [00:14<00:16, 18.17it/s] 48%|████▊ | 273/564 [00:14<00:15, 18.41it/s] 49%|████▉ | 275/564 [00:14<00:15, 18.56it/s] 49%|████▉ | 277/564 [00:14<00:15, 18.74it/s] 49%|████▉ | 279/564 [00:15<00:15, 18.79it/s] 50%|████▉ | 281/564 [00:15<00:15, 18.75it/s] 50%|█████ | 283/564 [00:15<00:14, 18.97it/s] 51%|█████ | 285/564 [00:15<00:14, 18.98it/s] 51%|█████ | 287/564 [00:15<00:14, 18.91it/s] 51%|█████ | 289/564 [00:15<00:14, 18.75it/s] 52%|█████▏ | 291/564 [00:15<00:14, 18.85it/s] 52%|█████▏ | 293/564 [00:15<00:14, 18.83it/s] 52%|█████▏ | 295/564 [00:15<00:14, 19.01it/s] 53%|█████▎ | 297/564 [00:16<00:14, 19.02it/s] 53%|█████▎ | 299/564 [00:16<00:14, 18.90it/s] 53%|█████▎ | 301/564 [00:16<00:13, 18.89it/s] 54%|█████▎ | 303/564 [00:16<00:13, 18.91it/s] 54%|█████▍ | 305/564 [00:16<00:13, 18.87it/s] 54%|█████▍ | 307/564 [00:16<00:13, 18.72it/s] 55%|█████▍ | 309/564 [00:16<00:13, 18.63it/s] 55%|█████▌ | 311/564 [00:16<00:13, 18.70it/s] 55%|█████▌ | 313/564 [00:16<00:13, 18.74it/s] 56%|█████▌ | 315/564 [00:16<00:13, 18.83it/s] 56%|█████▌ | 317/564 [00:17<00:13, 18.75it/s] 57%|█████▋ | 319/564 [00:17<00:13, 18.67it/s] 57%|█████▋ | 321/564 [00:17<00:13, 18.54it/s] 57%|█████▋ | 323/564 [00:17<00:12, 18.55it/s] 58%|█████▊ | 325/564 [00:17<00:13, 18.20it/s] 58%|█████▊ | 327/564 [00:17<00:12, 18.33it/s] 58%|█████▊ | 329/564 [00:17<00:12, 18.50it/s] 59%|█████▊ | 331/564 [00:17<00:12, 18.49it/s] 59%|█████▉ | 333/564 [00:17<00:12, 18.40it/s] 59%|█████▉ | 335/564 [00:18<00:12, 18.33it/s] 60%|█████▉ | 337/564 [00:18<00:12, 18.28it/s] 60%|██████ | 339/564 [00:18<00:12, 18.59it/s] 60%|██████ | 341/564 [00:18<00:11, 18.72it/s] 61%|██████ | 343/564 [00:18<00:11, 18.77it/s] 61%|██████ | 345/564 [00:18<00:11, 18.95it/s] 62%|██████▏ | 347/564 [00:18<00:11, 18.91it/s] 62%|██████▏ | 349/564 [00:18<00:11, 18.87it/s] 62%|██████▏ | 351/564 [00:18<00:11, 18.91it/s] 63%|██████▎ | 353/564 [00:19<00:11, 18.87it/s] 63%|██████▎ | 355/564 [00:19<00:11, 18.77it/s] 63%|██████▎ | 357/564 [00:19<00:10, 18.83it/s] 64%|██████▎ | 359/564 [00:19<00:10, 18.89it/s] 64%|██████▍ | 361/564 [00:19<00:10, 18.91it/s] 64%|██████▍ | 363/564 [00:19<00:10, 18.54it/s] 65%|██████▍ | 365/564 [00:19<00:10, 18.54it/s] 65%|██████▌ | 367/564 [00:19<00:10, 18.60it/s] 65%|██████▌ | 369/564 [00:19<00:10, 18.71it/s] 66%|██████▌ | 371/564 [00:19<00:10, 18.78it/s] 66%|██████▌ | 373/564 [00:20<00:10, 18.84it/s] 66%|██████▋ | 375/564 [00:20<00:10, 18.79it/s] 67%|██████▋ | 377/564 [00:20<00:09, 18.91it/s] 67%|██████▋ | 379/564 [00:20<00:09, 18.88it/s] 68%|██████▊ | 381/564 [00:20<00:09, 18.88it/s] 68%|██████▊ | 383/564 [00:20<00:09, 18.86it/s] 68%|██████▊ | 385/564 [00:20<00:09, 18.80it/s] 69%|██████▊ | 387/564 [00:20<00:09, 18.88it/s] 69%|██████▉ | 389/564 [00:20<00:09, 18.84it/s] 69%|██████▉ | 391/564 [00:21<00:09, 18.77it/s] 70%|██████▉ | 393/564 [00:21<00:09, 18.74it/s] 70%|███████ | 395/564 [00:21<00:08, 18.82it/s] 70%|███████ | 397/564 [00:21<00:08, 18.90it/s] 71%|███████ | 399/564 [00:21<00:08, 18.69it/s] 71%|███████ | 401/564 [00:21<00:08, 18.60it/s] 71%|███████▏ | 403/564 [00:21<00:08, 18.64it/s] 72%|███████▏ | 405/564 [00:21<00:08, 18.64it/s] 72%|███████▏ | 407/564 [00:21<00:08, 18.71it/s] 73%|███████▎ | 409/564 [00:22<00:08, 18.68it/s] 73%|███████▎ | 411/564 [00:22<00:08, 18.66it/s] 73%|███████▎ | 413/564 [00:22<00:08, 18.61it/s] 74%|███████▎ | 415/564 [00:22<00:07, 18.70it/s] 74%|███████▍ | 417/564 [00:22<00:07, 18.69it/s] 74%|███████▍ | 419/564 [00:22<00:07, 18.43it/s] 75%|███████▍ | 421/564 [00:22<00:07, 18.61it/s] 75%|███████▌ | 423/564 [00:22<00:07, 18.66it/s] 75%|███████▌ | 425/564 [00:22<00:07, 18.68it/s] 76%|███████▌ | 427/564 [00:22<00:07, 18.73it/s] 76%|███████▌ | 429/564 [00:23<00:07, 18.69it/s] 76%|███████▋ | 431/564 [00:23<00:07, 18.64it/s] 77%|███████▋ | 433/564 [00:23<00:06, 18.80it/s] 77%|███████▋ | 435/564 [00:23<00:06, 18.74it/s] 77%|███████▋ | 437/564 [00:23<00:06, 18.34it/s] 78%|███████▊ | 439/564 [00:23<00:06, 18.33it/s] 78%|███████▊ | 441/564 [00:23<00:06, 18.43it/s] 79%|███████▊ | 443/564 [00:23<00:06, 18.46it/s] 79%|███████▉ | 445/564 [00:23<00:06, 18.48it/s] 79%|███████▉ | 447/564 [00:24<00:06, 18.55it/s] 80%|███████▉ | 449/564 [00:24<00:06, 18.66it/s] 80%|███████▉ | 451/564 [00:24<00:06, 18.74it/s] 80%|████████ | 453/564 [00:24<00:05, 18.94it/s] 81%|████████ | 455/564 [00:24<00:05, 18.88it/s] 81%|████████ | 457/564 [00:24<00:05, 18.60it/s] 81%|████████▏ | 459/564 [00:24<00:05, 18.45it/s] 82%|████████▏ | 461/564 [00:24<00:05, 18.57it/s] 82%|████████▏ | 463/564 [00:24<00:05, 18.69it/s] 82%|████████▏ | 465/564 [00:25<00:05, 18.75it/s] 83%|████████▎ | 467/564 [00:25<00:05, 18.73it/s] 83%|████████▎ | 469/564 [00:25<00:05, 18.91it/s] 84%|████████▎ | 471/564 [00:25<00:04, 18.84it/s] 84%|████████▍ | 473/564 [00:25<00:04, 18.78it/s] 84%|████████▍ | 475/564 [00:25<00:04, 18.82it/s] 85%|████████▍ | 477/564 [00:25<00:04, 18.87it/s] 85%|████████▍ | 479/564 [00:25<00:04, 18.77it/s] 85%|████████▌ | 481/564 [00:25<00:04, 18.75it/s] 86%|████████▌ | 483/564 [00:25<00:04, 18.75it/s] 86%|████████▌ | 485/564 [00:26<00:04, 18.75it/s] 86%|████████▋ | 487/564 [00:26<00:04, 18.79it/s] 87%|████████▋ | 489/564 [00:26<00:03, 18.85it/s] 87%|████████▋ | 491/564 [00:26<00:03, 18.86it/s] 87%|████████▋ | 493/564 [00:26<00:03, 18.83it/s] 88%|████████▊ | 495/564 [00:26<00:03, 18.95it/s] 88%|████████▊ | 497/564 [00:26<00:03, 18.96it/s] 88%|████████▊ | 499/564 [00:26<00:03, 18.93it/s] 89%|████████▉ | 501/564 [00:26<00:03, 19.13it/s] 89%|████████▉ | 503/564 [00:27<00:03, 19.09it/s] 90%|████████▉ | 505/564 [00:27<00:03, 19.10it/s] 90%|████████▉ | 507/564 [00:27<00:02, 19.17it/s] 90%|█████████ | 509/564 [00:27<00:02, 19.14it/s] 91%|█████████ | 511/564 [00:27<00:02, 19.11it/s] 91%|█████████ | 513/564 [00:27<00:02, 19.10it/s] 91%|█████████▏| 515/564 [00:27<00:02, 19.01it/s] 92%|█████████▏| 517/564 [00:27<00:02, 19.01it/s] 92%|█████████▏| 519/564 [00:27<00:02, 18.99it/s] 92%|█████████▏| 521/564 [00:27<00:02, 18.92it/s] 93%|█████████▎| 523/564 [00:28<00:02, 18.92it/s] 93%|█████████▎| 525/564 [00:28<00:02, 18.98it/s] 93%|█████████▎| 527/564 [00:28<00:01, 19.13it/s] 94%|█████████▍| 529/564 [00:28<00:01, 18.89it/s] 94%|█████████▍| 531/564 [00:28<00:01, 18.97it/s] 95%|█████████▍| 533/564 [00:28<00:01, 18.98it/s] 95%|█████████▍| 535/564 [00:28<00:01, 18.90it/s] 95%|█████████▌| 537/564 [00:28<00:01, 18.86it/s] 96%|█████████▌| 539/564 [00:28<00:01, 18.80it/s] 96%|█████████▌| 541/564 [00:29<00:01, 18.81it/s] 96%|█████████▋| 543/564 [00:29<00:01, 18.85it/s] 97%|█████████▋| 545/564 [00:29<00:01, 18.93it/s] 97%|█████████▋| 547/564 [00:29<00:00, 19.02it/s] 97%|█████████▋| 549/564 [00:29<00:00, 18.95it/s] 98%|█████████▊| 551/564 [00:29<00:00, 18.62it/s] 98%|█████████▊| 553/564 [00:29<00:00, 18.75it/s] 98%|█████████▊| 555/564 [00:29<00:00, 18.77it/s] 99%|█████████▉| 557/564 [00:29<00:00, 18.88it/s] 99%|█████████▉| 559/564 [00:29<00:00, 18.91it/s] 99%|█████████▉| 561/564 [00:30<00:00, 18.95it/s] 100%|█████████▉| 563/564 [00:30<00:00, 18.87it/s] 100%|██████████| 564/564 [00:30<00:00, 18.65it/s] ffmpeg -y -v warning -r 25.0 -f image2 -i /src/results/tmplxnmwn1zsun_tmp9xfjhifksun/%08d.png -vcodec libx264 -vf format=rgb24,scale=out_color_matrix=bt709,format=yuv420p -crf 18 temp.mp4 ffmpeg -y -v warning -i /tmp/tmp9xfjhifksun.wav -i temp.mp4 /src/results/tmplxnmwn1zsun_tmp9xfjhifksun.mp4 [aist#0:0/pcm_s16le @ 0x55c2d0d10ec0] Guessed Channel Layout: mono result is save to /src/results/tmplxnmwn1zsun_tmp9xfjhifksun.mp4
Want to make some of these yourself?
Run this model