process data

[yihaoyao402]

hi, when i use VCTK dataset, process has a problem called "UnboundLocalError: local variable 'f0' referenced before assignment"
but using LJSpeech is ok. By the way ,when i train the naive model by LJSpeech, it comes to a problem called " GaussiDiffusion has no attribute cond in torch", is this caused by torch version?

[quiteconfused]

i too get the VCTK preprocess error when i follow the instructions .... going to try right now with LJSpeech

2023-03-01 18:58:07.058104: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1613] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 21092 MB memory: -> device: 0, name: NVIDIA GeForce RTX 3090, pci bus id: 0000:0b:00.0, compute capability: 8.6 Processing Data ... 0%|▏ | 1/462 [00:00<00:01, 305.46it/s] 0%| | 0/109 [00:00<?, ?it/s]Traceback (most recent call last): File "/home/XXXXXXXXXXX/DiffGAN-TTS/./preprocess.py", line 19, in <module> preprocessor.build_from_path() File "/home/XXXXXXXXXXX/DiffGAN-TTS/preprocessor/preprocessor.py", line 133, in build_from_path if len(f0) > 0: UnboundLocalError: local variable 'f0' referenced before assignment

[yihaoyao402]

hi, sorry to bother you, did you find the way to solve this problem? @quiteconfused

[isjwdu]

same error