runtime error

Exit code: 1. Reason: PyTorch was not found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. PyTorch was not found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. config.json: 0%| | 0.00/2.25k [00:00<?, ?B/s] config.json: 100%|██████████| 2.25k/2.25k [00:00<00:00, 5.68MB/s] Traceback (most recent call last): File "/app/app.py", line 6, in <module> asr = pipeline( "automatic-speech-recognition", ...<2 lines>... device=-1 # CPU; haddii GPU doorato, u beddel 0 ) File "/usr/local/lib/python3.13/site-packages/transformers/pipelines/__init__.py", line 797, in pipeline if isinstance(dtype, str) and hasattr(torch, dtype): ^^^^^ NameError: name 'torch' is not defined

Container logs: