Spaces:

---

ACE-Step

/

Ace-Step-v1.5

like 432

Running on Zero

When using cover mode and a source audio + reference track

and model acestep-v15-turbo

the following error results:

❌ Error: Expected all tensors to be on the same device, but got mat2 is on cpu, different from other tensors on cuda:0 (when checking argument in method wrapper_CUDA_mm)
Traceback (most recent call last):
File "/home/user/app/acestep/handler.py", line 2884, in generate_music
outputs = self.service_generate(
File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
File "/home/user/app/acestep/handler.py", line 2539, in service_generate
encoder_hidden_states, encoder_attention_mask, context_latents = self.model.prepare_condition(
File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
File "/home/user/.cache/huggingface/modules/transformers_modules/acestep_hyphen_v15_hyphen_turbo/modeling_acestep_v15_turbo.py", line 1623, in prepare_condition
encoder_hidden_states, encoder_attention_mask = self.encoder(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.cache/huggingface/modules/transformers_modules/acestep_hyphen_v15_hyphen_turbo/modeling_acestep_v15_turbo.py", line 1537, in forward
text_hidden_states = self.text_projector(text_hidden_states)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 134, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: Expected all tensors to be on the same device, but got mat2 is on cpu, different from other tensors on cuda:0 (when checking argument in method wrapper_CUDA_mm)