Convert RVC failed with TTS

[Kerorowong]

Get this error while doing TTS

To create a public link, set share=True in launch(). TTS with zh-TW-HsiaoChenNeural completed. Output TTS file: 'F:\VA\Applio-3.0.8\assets\audios\tts_output.wav'

Traceback (most recent call last): File "F:\VA\Applio-3.0.8\rvc\infer\infer.py", line 251, in get_vc(model_path, 0) File "F:\VA\Applio-3.0.8\rvc\infer\infer.py", line 228, in get_vc net_g = net_g.half() File "F:\VA\Applio-3.0.8\env\lib\site-packages\torch\nn\modules\module.py", line 1014, in half return self._apply(lambda t: t.half() if t.is_floating_point() else t) File "F:\VA\Applio-3.0.8\env\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply module._apply(fn) File "F:\VA\Applio-3.0.8\env\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply module._apply(fn) File "F:\VA\Applio-3.0.8\env\lib\site-packages\torch\nn\modules\module.py", line 833, in _apply param_applied = fn(param) File "F:\VA\Applio-3.0.8\env\lib\site-packages\torch\nn\modules\module.py", line 1014, in return self._apply(lambda t: t.half() if t.is_floating_point() else t) RuntimeError: CUDA error: operation not supported CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. Traceback (most recent call last): File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\queueing.py", line 495, in call_prediction output = await route_utils.call_process_api( File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api output = await app.get_blocks().process_api( File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\blocks.py", line 1570, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\blocks.py", line 1456, in postprocess_data outputs_cached = processing_utils.move_files_to_cache( File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\processing_utils.py", line 265, in move_files_to_cache return client_utils.traverse(data, _move_to_cache, client_utils.is_file_obj) File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio_client\utils.py", line 919, in traverse return func(json_obj) File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\processing_utils.py", line 257, in _move_to_cache temp_file_path = move_resource_to_block_cache(payload.path, block) File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\processing_utils.py", line 234, in move_resource_to_block_cache return block.move_resource_to_block_cache(url_or_file_path) File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\blocks.py", line 258, in move_resource_to_block_cache temp_file_path = processing_utils.save_file_to_cache( File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\processing_utils.py", line 170, in save_file_to_cache temp_dir = hash_file(file_path) File "F:\VA\Applio-3.0.8\env\lib\site-packages\gradio\processing_utils.py", line 102, in hash_file with open(file_path, "rb") as f: FileNotFoundError: [Errno 2] No such file or directory: 'F:\\VA\\Applio-3.0.8\\assets\\audios\\tts_rvc_output.wav'

[blaisewf]

whats your hardware?

[Kerorowong]

whats your hardware?

Intel(R) Core(TM) i5-10400F CPU @ 2.90GHz 2.90 GHz AMD rx6600 xt

[blaisewf]

ok, try to move applio to your C disk and use the compiled version

[Kerorowong]

Theme Loaded: Applio Running on local URL: http://127.0.0.1:6969

To create a public link, set share=True in launch(). DoraemonJap.pth saved in C:\VA\ApplioV3.0.9\logs\DoraemonJap added_IVF1499_Flat_nprobe_1_DoraemonJap_v2.index saved in C:\VA\ApplioV3.0.9\logs\DoraemonJap TTS with zh-TW-YunJheNeural completed. Output TTS file: 'C:\VA\ApplioV3.0.9\assets\audios\tts_output.wav'

Traceback (most recent call last): File "C:\VA\ApplioV3.0.9\rvc\infer\infer.py", line 260, in get_vc(model_path, 0) File "C:\VA\ApplioV3.0.9\rvc\infer\infer.py", line 236, in get_vc net_g = net_g.half() File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 1014, in half return self._apply(lambda t: t.half() if t.is_floating_point() else t) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply module._apply(fn) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply module._apply(fn) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 833, in _apply param_applied = fn(param) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 1014, in return self._apply(lambda t: t.half() if t.is_floating_point() else t) RuntimeError: CUDA error: operation not supported CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. Traceback (most recent call last): File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\queueing.py", line 495, in call_prediction output = await route_utils.call_process_api( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\route_utils.py", line 230, in call_process_api output = await app.get_blocks().process_api( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\blocks.py", line 1599, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\blocks.py", line 1453, in postprocess_data outputs_cached = processing_utils.move_files_to_cache( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 267, in move_files_to_cache return client_utils.traverse(data, _move_to_cache, client_utils.is_file_obj) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio_client\utils.py", line 981, in traverse return func(json_obj) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 259, in _move_to_cache temp_file_path = move_resource_to_block_cache(payload.path, block) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 236, in move_resource_to_block_cache return block.move_resource_to_block_cache(url_or_file_path) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\blocks.py", line 257, in move_resource_to_block_cache temp_file_path = processing_utils.save_file_to_cache( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 170, in save_file_to_cache temp_dir = hash_file(file_path) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 102, in hash_file with open(file_path, "rb") as f: FileNotFoundError: [Errno 2] No such file or directory: 'C:\\VA\\ApplioV3.0.9\\assets\\audios\\tts_rvc_output.wav' TTS with zh-TW-YunJheNeural completed. Output TTS file: 'C:\VA\ApplioV3.0.9\assets\audios\tts_output.wav' Traceback (most recent call last): File "C:\VA\ApplioV3.0.9\rvc\infer\infer.py", line 260, in get_vc(model_path, 0) File "C:\VA\ApplioV3.0.9\rvc\infer\infer.py", line 236, in get_vc net_g = net_g.half() File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 1014, in half return self._apply(lambda t: t.half() if t.is_floating_point() else t) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply module._apply(fn) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 810, in _apply module._apply(fn) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 833, in _apply param_applied = fn(param) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\torch\nn\modules\module.py", line 1014, in return self._apply(lambda t: t.half() if t.is_floating_point() else t) RuntimeError: CUDA error: operation not supported CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. Traceback (most recent call last): File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\queueing.py", line 495, in call_prediction output = await route_utils.call_process_api( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\route_utils.py", line 230, in call_process_api output = await app.get_blocks().process_api( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\blocks.py", line 1599, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\blocks.py", line 1453, in postprocess_data outputs_cached = processing_utils.move_files_to_cache( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 267, in move_files_to_cache return client_utils.traverse(data, _move_to_cache, client_utils.is_file_obj) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio_client\utils.py", line 981, in traverse return func(json_obj) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 259, in _move_to_cache temp_file_path = move_resource_to_block_cache(payload.path, block) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 236, in move_resource_to_block_cache return block.move_resource_to_block_cache(url_or_file_path) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\blocks.py", line 257, in move_resource_to_block_cache temp_file_path = processing_utils.save_file_to_cache( File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 170, in save_file_to_cache temp_dir = hash_file(file_path) File "C:\VA\ApplioV3.0.9\env\lib\site-packages\gradio\processing_utils.py", line 102, in hash_file with open(file_path, "rb") as f: FileNotFoundError: [Errno 2] No such file or directory: 'C:\\VA\\ApplioV3.0.9\\assets\\audios\\tts_rvc_output.wav'

Use the compiled version in C drive, still having the same error

[blaisewf]

It looks like it might be more of a compatibility bug with your computer, check forums that discuss similar things.

https://discuss.huggingface.co/t/cuda-error-device-side-assert-triggered-after-a-certain-steps/47597/5