your project does not run in a virtual environment

[vladgohn]

Python39 Cuda11.3

|----------------------------------------| 0.00% [0/749 00:00<?]

AttributeError Traceback (most recent call last)
Cell In[10], line 3
1 # this is very slow right now since our inference code is not very optimized
2 # but even without this crucial optimization it is still better than real-time on an RTX 4090
----> 3 pipe.generate_to_notebook("""
4 This is the first demo of Whisper Speech, a fully open source text-to-speech model trained by Collabora and Lion on the Juwels supercomputer.
5 """)

File d:\TTS WORK\WhisperSpeech\whisperspeech\pipeline.py:32, in Pipeline.generate_to_notebook(self, text, speaker)
31 def generate_to_notebook(self, text, speaker="8699"):
---> 32 self.vocoder.decode_to_notebook(self.generate_atoks(text, speaker))

File d:\TTS WORK\WhisperSpeech\whisperspeech\pipeline.py:21, in Pipeline.generate_atoks(self, text, speaker)
19 def generate_atoks(self, text, speaker="8699"):
20 text = text.replace("\n", " ")
---> 21 stoks = self.t2s.generate(text, cps=14)
22 atoks = self.s2a.generate(stoks, [speaker])
23 return atoks

File d:\TTS WORK\WhisperSpeech\venv\lib\site-packages\torch\autograd\grad_mode.py:27, in _DecoratorContextManager.call..decorate_context(*args, **kwargs)
24 @functools.wraps(func)
25 def decorate_context(*args, **kwargs):
26 with self.clone():
---> 27 return func(*args, **kwargs)
...
112 # previously we've returned q@k which we don't have now
113 # since it's not actually used anywhere else, let's just keep two return values for compatibility
114 return wv.permute(0, 2, 1, 3).flatten(start_dim=2), None

AttributeError: module 'torch.nn.functional' has no attribute 'scaled_dot_product_attention'
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

[jpc]

Hey, this looks like maybe you are using an old version of PyTorch? I believe it was added in version 2.0.

How are you creating the virtual environment?