Open kenil261615 opened 1 year ago
Found GPU NVIDIA GeForce GTX 1650 Ti , force to fp32 Use Language: en_US Running on local URL: http://0.0.0.0:7879 loading weights/arijit.pth gin_channels: 256 self.spk_embed_dim: 109 Traceback (most recent call last): File "C:\Users\HP\Downloads\AI\Retrieval-based-Voice-Conversion-WebUI\lib\audio.py", line 14, in load_audio ffmpeg.input(file, threads=0) File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\site-packages\ffmpeg_run.py", line 313, in run process = run_async( File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\site-packages\ffmpeg_run.py", line 284, in run_async return subprocess.Popen( File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\subprocess.py", line 947, in init self._execute_child(args, executable, preexec_fn, close_fds, File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\subprocess.py", line 1416, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] The system cannot find the file specified
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "C:\Users\HP\Downloads\AI\Retrieval-based-Voice-Conversion-WebUI\infer-web.py", line 188, in vc_single audio = load_audio(input_audio_path, 16000) File "C:\Users\HP\Downloads\AI\Retrieval-based-Voice-Conversion-WebUI\lib\audio.py", line 19, in load_audio raise RuntimeError(f"Failed to load audio: {e}") RuntimeError: Failed to load audio: [WinError 2] The system cannot find the file specified
Traceback (most recent call last): File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\blocks.py", line 1434, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\blocks.py", line 1341, in postprocess_data prediction_value = block.postprocess(prediction_value) File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\components\audio.py", line 345, in postprocess file_path = self.audio_to_temp_file( File "C:\Users\HP\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\components\base.py", line 325, in audio_to_temp_file temp_dir = Path(self.DEFAULT_TEMP_DIR) / self.hash_bytes(data.tobytes()) AttributeError: 'NoneType' object has no attribute 'tobytes'
Same error for me. Id appreciate any ideas :)
You input a wrong audio path.
pip install --upgrade --no-deps --force-reinstall torchcrepe
Fixed it for me
You input a wrong audio path.
That is not the case, my path is correct unfortunately. The fix proposed by @Volt24 did not work for me :(
You input a wrong audio path.
i believe this but which one should be the correct path ?
For me, reinstalling the whole package fixed.
Move the rmvpe.pt to the asset/rmvpe/rmvpe.pt fixed my issue. The guide in the README was quite miss leading. Don't put rmvpe.pt in the root folder.
I'm also having the same. I'm using the portable version of rvc. I have solved another problem before this but I can't figure this out.
Previously I had ' attributeerror none type object has no attribute 'dtype' '. I installed the required packages local python in my os then I copied gradio and other packs from my local python directory to the library folder in the runtime folder. 'Dtype ' error was fixed. But I'm getting this error now.
For me, reinstalling the whole package fixed.
If so do we have to update packs?
I can clone my voice to a small song( hardly 10sec). If I clone my voice to a 4-5 minute , it gives error.
For a check Are you all using rvc with required system?
I think when your memory is not enough to hold the entire audio file ,it attempts to write it in a file. In my case I am a iris xe graphics user I can clone a 5 sec file with out filling the vram. But the longer conversion fills my memory and gives error. Then why don't you guys trim the audio to a smaller size then try . GeForce GTX 1650 also have 4gb vram like me.
Found GPU NVIDIA GeForce GTX 1650 Ti , force to fp32 Use Language: en_US Running on local URL: http://0.0.0.0:7879 loading weights/arijit.pth gin_channels: 256 self.spk_embed_dim: 109