ttPrivacy
commented
6 months ago 报错信息
(EmotiVoice) root@DESKTOP-O06UKC6:/home/tts/EmotiVoice-main# python inference_am_vocoder_joint.py --logdir prompt_tts_open_source_joint --config_folder config/joint --checkpoint g_00140000 --test_file data/inference/text
run!
Traceback (most recent call last):
File "inference_am_vocoder_joint.py", line 156, in
window的wsl2 cuda 11.6 torch==1.13.0+cu116 torchvision==0.14.0+cu116 torchaudio==0.13.0 在运行官方案例的时候报错了 代码
TEXT=data/inference/text python inference_am_vocoder_joint.py \ --logdir prompt_tts_open_source_joint \ --config_folder config/joint \ --checkpoint g_00140000 \ --test_file $TEXT报错信息如下run! Traceback (most recent call last): File "inference_am_vocoder_joint.py", line 156, in <module> main(args, config) File "inference_am_vocoder_joint.py", line 61, in main model_CKPT = torch.load(config.style_encoder_ckpt, map_location="cpu") File "/root/anaconda3/envs/EmotiVoice/lib/python3.8/site-packages/torch/serialization.py", line 795, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/root/anaconda3/envs/EmotiVoice/lib/python3.8/site-packages/torch/serialization.py", line 1002, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'.请大佬解答，谢谢~