Rudrabha / Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs
https://synclabs.so
9.74k stars 2.11k forks source link

FileNotFoundError: [WinError 2] the specified file cannot be found #663

Open asgard13373 opened 2 months ago

asgard13373 commented 2 months ago

///(I don't understand python and its libraries. my knowledge is limited to ctrl c + v, thanks in advance)

I installed the model and the checkpoint according to the instructions, and when generating the finished video, I got the following log: File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\torch\nn\modules\module.py", line 2153, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for s3fd: █████████████████████████████████████████████████████████████| 11/11 [01:18<00:00, 7.12s/it] Traceback (most recent call last): File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\gradio\routes.py", line 534, in predict output = await route_utils.call_process_api( File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api output = await app.get_blocks().process_api( File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\gradio\blocks.py", line 1550, in process_api result = await self.call_function( File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\gradio\blocks.py", line 1185, in call_function prediction = await anyio.to_thread.run_sync( File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\anyio_backends_asyncio.py", line 2144, in run_sync_in_worker_thread return await future File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\anyio_backends_asyncio.py", line 851, in run result = context.run(func, args) File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\site-packages\gradio\utils.py", line 661, in wrapper response = f(args, *kwargs) File "D:\hhh\wav2lip\ui.py", line 246, in generate inference("checkpoints/" + checkpoint + ".pth", video.name, grAudio.name, pads, resize_factor, no_smooth) File "D:\hhh\wav2lip\ui.py", line 219, in inference subprocess.call(command, shell=platform.system() != 'Windows') File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\subprocess.py", line 345, in call with Popen(popenargs, **kwargs) as p: File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\subprocess.py", line 971, in init self._execute_child(args, executable, preexec_fn, close_fds, File "C:\Users\asgar\Miniconda3\envs\wav2lip\lib\subprocess.py", line 1456, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] Не удается найти указанный файл

aliazmn commented 1 month ago

same issue any progress?

UGarCil commented 1 week ago

I ran into this issue when trying the Wav2Lip algorithm. Make sure to install your dependency (in my example ffmpeg) using conda install ffmpeg

The issue is likely caused by python trying to run a process in the command line for a module that doesn't have the binaries in the bin folder of your environment. In my case (Windows), it had to be in C:\Users\myname.conda\envs\wav2lip\Library\bin\ffmpeg.exe

To test whether it's in your binaries, you can open the command prompt and type "where ffmpeg"