runtime error

Exit code: 1. Reason: ... 2024-09-18 17:15:39,529 INFO skip building fst for zh_normalizer ... 2024-09-18 17:15:40,003 WETEXT INFO found existing fst: /usr/local/lib/python3.10/site-packages/tn/en_tn_tagger.fst 2024-09-18 17:15:40,003 INFO found existing fst: /usr/local/lib/python3.10/site-packages/tn/en_tn_tagger.fst 2024-09-18 17:15:40,003 WETEXT INFO /usr/local/lib/python3.10/site-packages/tn/en_tn_verbalizer.fst 2024-09-18 17:15:40,003 INFO /usr/local/lib/python3.10/site-packages/tn/en_tn_verbalizer.fst 2024-09-18 17:15:40,003 WETEXT INFO skip building fst for en_normalizer ... 2024-09-18 17:15:40,003 INFO skip building fst for en_normalizer ... Traceback (most recent call last): File "/home/user/app/app.py", line 5, in <module> from tabs.audios.ui import audio_tab File "/home/user/app/tabs/audios/ui.py", line 4, in <module> from .events import * File "/home/user/app/tabs/audios/events.py", line 14, in <module> from .load_models import * File "/home/user/app/tabs/audios/load_models.py", line 27, in <module> device, df_model, df_state, cosyvoice, cosyvoice_sft, sft_speakers, cosyvoice_instruct = init_sys() File "/home/user/app/tabs/audios/load_models.py", line 18, in init_sys cosyvoice= CosyVoice('FunAudioLLM/CosyVoice-300M') File "/home/user/app/tabs/audios/modules/CosyVoice/cosyvoice/cli/cosyvoice.py", line 40, in __init__ self.model = CosyVoiceModel(configs['llm'], configs['flow'], configs['hift']) File "/home/user/app/tabs/audios/modules/CosyVoice/cosyvoice/cli/model.py", line 46, in __init__ self.llm_context = torch.cuda.stream(torch.cuda.Stream(self.device)) if torch.cuda.is_available() else nullcontext() File "/usr/local/lib/python3.10/site-packages/torch/cuda/streams.py", line 37, in __new__ return super().__new__(cls, priority=priority, **kwargs) RuntimeError: CUDA error: no CUDA-capable device is detected Device-side assertions were explicitly omitted for this error check; the error probably arose while initializing the DSA handlers.

Container logs: