Error on Use Reference Video in the new stand-alone version

[ShmuelRonen]

I put a source image, input audio and a Reference Video and get an error

Here is the CMD list:

using safetensor as default {'checkpoint': 'checkpoints\SadTalker_V0.0.2_512.safetensors', 'dir_of_BFM_fitting': 'src/config', 'audio2pose_yaml_path': 'src/config\auido2pose.yaml', 'audio2exp_yaml_path': 'src/config\auido2exp.yaml', 'use_safetensor': True, 'mappingnet_checkpoint': 'checkpoints\mapping_00109-model.pth.tar', 'facerender_yaml': 'src/config\facerender_still.yaml'} C:\Users\Public\Documents\Wondershare\CreatorTemp\gradio\1f0ff394303a1883f0d075f8519a22f31dee8dd0\image.png new audiopath: ./results/9a0aff4b-e486-456c-b4a3-bbeda61ae663\look6.mp4.wav [out#0/wav @ 000001fea37787c0] Output file does not contain any stream landmark Det:: 100%|███████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 12.35it/s] 3DMM Extraction In Video:: 100%|███████████████████████████████████████████████████████| 1/1 [00:00<00:00, 62.50it/s] using ref video for genreation 3DMM Extraction for the reference video providing pose landmark Det:: 100%|███████████████████████████████████████████████████████████████| 291/291 [00:23<00:00, 12.55it/s] 3DMM Extraction In Video:: 100%|███████████████████████████████████████████████████| 291/291 [00:04<00:00, 64.85it/s] Face Renderer:: 100%|██████████████████████████████████████████████████████████████| 146/146 [01:22<00:00, 1.76it/s] Traceback (most recent call last): File "C:\sad\SadTalker\venv\lib\site-packages\gradio\routes.py", line 437, in run_predict output = await app.get_blocks().process_api( File "C:\sad\SadTalker\venv\lib\site-packages\gradio\blocks.py", line 1346, in process_api result = await self.call_function( File "C:\sad\SadTalker\venv\lib\site-packages\gradio\blocks.py", line 1074, in call_function prediction = await anyio.to_thread.run_sync( File "C:\sad\SadTalker\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "C:\sad\SadTalker\venv\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "C:\sad\SadTalker\venv\lib\site-packages\anyio_backends_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\sad\SadTalker\src\gradio_demo.py", line 139, in test return_path = self.animate_from_coeff.generate(data, save_dir, pic_path, crop_info, enhancer='gfpgan' if use_enhancer else None, preprocess=preprocess, img_size=size) File "C:\sad\SadTalker\src\facerender\animate.py", line 215, in generate sound = AudioSegment.from_file(audio_path) File "C:\sad\SadTalker\venv\lib\site-packages\pydub\audio_segment.py", line 651, in from_file file, close_file = _fd_or_path_or_tempfile(file, 'rb', tempfile=False) File "C:\sad\SadTalker\venv\lib\site-packages\pydub\utils.py", line 60, in _fd_or_path_or_tempfile fd = open(fd, mode=mode) FileNotFoundError: [Errno 2] No such file or directory: './results/9a0aff4b-e486-456c-b4a3-bbeda61ae663\look6.mp4.wav'

[vinthony]

it seems your reference video does not contain any audio. Have you tested the pose or blink mode? it is running well?

[ShmuelRonen]

Thanks ! my mistake

[vinthony]

cool!

[imomin]

@ShmuelRonen I am running latest version from main branch. My web UI looks different than yours. I don't see "Reference Video" section.

[ShmuelRonen]

@ShmuelRonen I am running latest version from main branch. My web UI looks different than yours. I don't see "Reference Video" section.

You must install the new stand alone version.

[imomin]

No luck! Maybe, it's different for Mac? I followed the same steps (twice).

[ShmuelRonen]

No luck! Maybe, it's different for Mac? I followed the same steps (twice).

Try to install it on Linux under Mac