Model stuck in generation
#7
by
florianstrasser - opened
I installed "everything" - at least everything I know of. But sadly I'm not able to generate an audio clip yet... First it shows this promising log:
python script.py
`torch_dtype` is deprecated! Use `dtype` instead!
`torch_dtype` is deprecated! Use `dtype` instead!
Loading checkpoint shards: 100%|██████████████████| 4/4 [00:00<00:00, 14.12it/s]
Could not load config: kugelaudio/kugelaudio-0-open does not appear to have a file named preprocessor_config.json. Checkout 'https://huggingface.co/kugelaudio/kugelaudio-0-open/tree/main' for available files.. Using defaults.
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'Qwen2Tokenizer'.
The class this function is called from is 'KugelAudioTextTokenizer'.
Generating: 0%| | 3/2048 [00:22<3:55:47, 6.92s/it]
But after a while the generating part turns into this and is stuck in an "endless" loop, at least it wasn't finished after an hour:
kugelaudio-0-open % python script.py
`torch_dtype` is deprecated! Use `dtype` instead!
`torch_dtype` is deprecated! Use `dtype` instead!
Loading checkpoint shards: 100%|██████████████████| 4/4 [00:00<00:00, 14.12it/s]
Could not load config: kugelaudio/kugelaudio-0-open does not appear to have a file named preprocessor_config.json. Checkout 'https://huggingface.co/kugelaudio/kugelaudio-0-open/tree/main' for available files.. Using defaults.
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'Qwen2Tokenizer'.
The class this function is called from is 'KugelAudioTextTokenizer'.
/opt/anaconda3/lib/python3.13/site-packages/torch/nn/utils/weight_norm.py:144: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
WeightNorm.apply(module, name, dim)