walker-hyf / ECSS

Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling (Accepted by AAAI'2024)
MIT License
48 stars 4 forks source link

May I ask why this error occurred #4

Open xiaobai1086 opened 3 months ago

xiaobai1086 commented 3 months ago

tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0 Device of CompTransTTS: cuda Traceback (most recent call last): File "synthesize.py", line 218, in synthesize(device, model, args, configs, vocoder, batchs, control_values) File "synthesize.py", line 67, in synthesize output = model( File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/lanyun-tmp/ECSS/model/CompTransTTS.py", line 211, in forward for j in range(data["audio"].x.shape[0]): File "/usr/local/lib/python3.8/dist-packages/torch_geometric/data/storage.py", line 96, in getattr raise AttributeError( AttributeError: 'NodeStorage' object has no attribute 'x'

5Hyeons commented 1 month ago

https://github.com/walker-hyf/ECSS/blob/c1545fdb12ca56482de4ff3550dc47b81d9fe794/utils/tools.py#L202 I think this line should be commented out. then it works