Spaces:

mrfakename

/

E2-F5-TTS

like 1.22k

Running on Zero

runtime error
Exit code: 1. Reason: e https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
state_dict = torch.load(model_path, map_location="cpu")

ZeroGPU tensors packing: 0%| | 0.00/4.31G [00:00<?, ?B/s]

ZeroGPU tensors packing: 2%|▏ | 80.2M/4.31G [00:01<00:53, 79.2MB/s]

ZeroGPU tensors packing: 11%|█ | 467M/4.31G [00:02<00:14, 259MB/s] 

ZeroGPU tensors packing: 20%|██ | 865M/4.31G [00:03<00:10, 321MB/s]

ZeroGPU tensors packing: 29%|██▉ | 1.25G/4.31G [00:04<00:08, 344MB/s]

ZeroGPU tensors packing: 40%|████ | 1.73G/4.31G [00:05<00:06, 393MB/s]

ZeroGPU tensors packing: 56%|█████▋ | 2.42G/4.31G [00:06<00:03, 494MB/s]

ZeroGPU tensors packing: 77%|███████▋ | 3.32G/4.31G [00:07<00:01, 625MB/s]
ZeroGPU tensors packing: 100%|██████████| 4.31G/4.31G [00:07<00:00, 556MB/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Traceback (most recent call last):
  File "/home/user/app/app.py", line 794, in
  app.queue().launch()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 144, in launch
  return gr.Blocks.launch(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2581, in launch
  raise ValueError(
  ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.

Container logs:

===== Application Startup at 2024-10-18 05:05:03 =====

Using cuda device
/usr/local/lib/python3.10/site-packages/vocos/pretrained.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
state_dict = torch.load(model_path, map_location="cpu")

ZeroGPU tensors packing: 0%| | 0.00/4.31G [00:00<?, ?B/s]

ZeroGPU tensors packing: 4%|▍ | 172M/4.31G [00:01<00:24, 166MB/s]

ZeroGPU tensors packing: 11%|█ | 473M/4.31G [00:02<00:15, 243MB/s]

ZeroGPU tensors packing: 20%|█▉ | 853M/4.31G [00:03<00:11, 304MB/s]

ZeroGPU tensors packing: 33%|███▎ | 1.40G/4.31G [00:04<00:07, 400MB/s]

ZeroGPU tensors packing: 54%|█████▍ | 2.32G/4.31G [00:05<00:03, 585MB/s]

ZeroGPU tensors packing: 80%|███████▉ | 3.44G/4.31G [00:06<00:01, 766MB/s]
ZeroGPU tensors packing: 100%|██████████| 4.31G/4.31G [00:06<00:00, 646MB/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Traceback (most recent call last):
  File "/home/user/app/app.py", line 794, in
  app.queue().launch()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 144, in launch
  return gr.Blocks.launch(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2581, in launch
  raise ValueError(
  ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.
  Using cuda device
  /usr/local/lib/python3.10/site-packages/vocos/pretrained.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  state_dict = torch.load(model_path, map_location="cpu")

ZeroGPU tensors packing: 0%| | 0.00/4.31G [00:00<?, ?B/s]

ZeroGPU tensors packing: 6%|▌ | 260M/4.31G [00:01<00:15, 260MB/s]

ZeroGPU tensors packing: 16%|█▌ | 693M/4.31G [00:02<00:10, 362MB/s]

ZeroGPU tensors packing: 25%|██▍ | 1.07G/4.31G [00:03<00:08, 368MB/s]

ZeroGPU tensors packing: 34%|███▍ | 1.49G/4.31G [00:04<00:07, 386MB/s]

ZeroGPU tensors packing: 54%|█████▍ | 2.33G/4.31G [00:05<00:03, 539MB/s]

ZeroGPU tensors packing: 81%|████████ | 3.47G/4.31G [00:06<00:01, 740MB/s]
ZeroGPU tensors packing: 100%|██████████| 4.31G/4.31G [00:06<00:00, 653MB/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Traceback (most recent call last):
  File "/home/user/app/app.py", line 794, in
  app.queue().launch()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 144, in launch
  return gr.Blocks.launch(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2581, in launch
  raise ValueError(
  ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.
  Using cuda device
  /usr/local/lib/python3.10/site-packages/vocos/pretrained.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  state_dict = torch.load(model_path, map_location="cpu")

ZeroGPU tensors packing: 0%| | 0.00/4.31G [00:00<?, ?B/s]

ZeroGPU tensors packing: 5%|▌ | 228M/4.31G [00:01<00:18, 223MB/s]

ZeroGPU tensors packing: 17%|█▋ | 723M/4.31G [00:02<00:09, 381MB/s]

ZeroGPU tensors packing: 32%|███▏ | 1.39G/4.31G [00:03<00:05, 508MB/s]

ZeroGPU tensors packing: 58%|█████▊ | 2.49G/4.31G [00:04<00:02, 742MB/s]

ZeroGPU tensors packing: 90%|█████████ | 3.90G/4.31G [00:05<00:00, 982MB/s]
ZeroGPU tensors packing: 100%|██████████| 4.31G/4.31G [00:05<00:00, 820MB/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Traceback (most recent call last):
  File "/home/user/app/app.py", line 794, in
  app.queue().launch()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 144, in launch
  return gr.Blocks.launch(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2581, in launch
  raise ValueError(
  ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.
  Using cuda device
  /usr/local/lib/python3.10/site-packages/vocos/pretrained.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  state_dict = torch.load(model_path, map_location="cpu")

ZeroGPU tensors packing: 0%| | 0.00/4.31G [00:00<?, ?B/s]

ZeroGPU tensors packing: 3%|▎ | 126M/4.31G [00:01<00:33, 125MB/s]

ZeroGPU tensors packing: 8%|▊ | 332M/4.31G [00:02<00:23, 172MB/s]

ZeroGPU tensors packing: 13%|█▎ | 542M/4.31G [00:03<00:19, 189MB/s]

ZeroGPU tensors packing: 21%|██▏ | 916M/4.31G [00:04<00:13, 255MB/s]

ZeroGPU tensors packing: 31%|███ | 1.33G/4.31G [00:05<00:09, 311MB/s]

ZeroGPU tensors packing: 48%|████▊ | 2.08G/4.31G [00:06<00:04, 459MB/s]

ZeroGPU tensors packing: 62%|██████▏ | 2.69G/4.31G [00:07<00:03, 505MB/s]

ZeroGPU tensors packing: 81%|████████ | 3.49G/4.31G [00:08<00:01, 597MB/s]
ZeroGPU tensors packing: 100%|██████████| 4.31G/4.31G [00:08<00:00, 493MB/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Traceback (most recent call last):
  File "/home/user/app/app.py", line 794, in
  app.queue().launch()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 144, in launch
  return gr.Blocks.launch(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2581, in launch
  raise ValueError(
  ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.
  Using cuda device
  /usr/local/lib/python3.10/site-packages/vocos/pretrained.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  state_dict = torch.load(model_path, map_location="cpu")

ZeroGPU tensors packing: 0%| | 0.00/4.31G [00:00<?, ?B/s]

ZeroGPU tensors packing: 5%|▌ | 218M/4.31G [00:01<00:19, 206MB/s]

ZeroGPU tensors packing: 16%|█▋ | 710M/4.31G [00:02<00:09, 370MB/s]

ZeroGPU tensors packing: 31%|███ | 1.33G/4.31G [00:03<00:06, 483MB/s]

ZeroGPU tensors packing: 54%|█████▎ | 2.31G/4.31G [00:04<00:02, 675MB/s]

ZeroGPU tensors packing: 73%|███████▎ | 3.15G/4.31G [00:05<00:01, 736MB/s]
ZeroGPU tensors packing: 100%|██████████| 4.31G/4.31G [00:05<00:00, 729MB/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Traceback (most recent call last):
  File "/home/user/app/app.py", line 794, in
  app.queue().launch()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 144, in launch
  return gr.Blocks.launch(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2581, in launch
  raise ValueError(
  ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.
  Using cuda device
  /usr/local/lib/python3.10/site-packages/vocos/pretrained.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  state_dict = torch.load(model_path, map_location="cpu")

ZeroGPU tensors packing: 0%| | 0.00/4.31G [00:00<?, ?B/s]

ZeroGPU tensors packing: 2%|▏ | 80.2M/4.31G [00:01<00:53, 79.2MB/s]

ZeroGPU tensors packing: 11%|█ | 467M/4.31G [00:02<00:14, 259MB/s]

ZeroGPU tensors packing: 20%|██ | 865M/4.31G [00:03<00:10, 321MB/s]

ZeroGPU tensors packing: 29%|██▉ | 1.25G/4.31G [00:04<00:08, 344MB/s]

ZeroGPU tensors packing: 40%|████ | 1.73G/4.31G [00:05<00:06, 393MB/s]

ZeroGPU tensors packing: 56%|█████▋ | 2.42G/4.31G [00:06<00:03, 494MB/s]

ZeroGPU tensors packing: 77%|███████▋ | 3.32G/4.31G [00:07<00:01, 625MB/s]
ZeroGPU tensors packing: 100%|██████████| 4.31G/4.31G [00:07<00:00, 556MB/s]

• Running on local URL: http://0.0.0.0:7860, with SSR ⚡
  Traceback (most recent call last):
  File "/home/user/app/app.py", line 794, in
  app.queue().launch()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/gradio.py", line 144, in launch
  return gr.Blocks.launch(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2581, in launch
  raise ValueError(
  ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.
  Using cuda device