search

AlexandaJerry / whisper-vits-japanese

Vits Japanese with Whisper as data processor (you can train your VITS even you only have audios)
MIT License
160 stars 28 forks source link

IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1) #16

Open ChitoseSana6 opened 1 year ago

ChitoseSana6 commented 1 year ago

colab上torch版本1.12.1依旧报错 IndexError: Caught IndexError in DataLoader worker process 0. Original Traceback (most recent call last): File "/mnt/d/work/whisper-vits-japanese/env/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) File "/mnt/d/work/whisper-vits-japanese/env/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch return self.collate_fn(data) File "/mnt/d/work/whisper-vits-japanese/data_utils.py", line 121, in call print([x[1].size(1) for x in batch]) File "/mnt/d/work/whisper-vits-japanese/data_utils.py", line 121, in print([x[1].size(1) for x in batch]) IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1) 未对原代码做任何修改

AlexandaJerry commented 1 year ago

print([x[1].size(1) for x in batch]) 我看了data_utils.py 121没有写print啊 第121明明是个排序

使用新的代码然后先用isla数据集跑一遍看看，如果isla数据集没问题的话，应该就是有音频转频谱的时候出问题了