runtime error

Exit code: 1. Reason: ecoder.model.decoder.embed_positions.weights | UNEXPECTED | decoder.model.decoder.layers.{0...47}.encoder_attn.q_proj.weight | MISSING | decoder.model.decoder.layers.{0...47}.encoder_attn.k_proj.weight | MISSING | decoder.model.decoder.layers.{0...47}.encoder_attn.v_proj.weight | MISSING | decoder.model.decoder.layers.{0...47}.encoder_attn_layer_norm.weight | MISSING | decoder.model.decoder.layers.{0...47}.encoder_attn.out_proj.weight | MISSING | decoder.model.decoder.layers.{0...47}.encoder_attn_layer_norm.bias | MISSING | Notes: - UNEXPECTED :can be ignored when loading from different task/architecture; not ok if you expect identical arch. - MISSING :those params were newly initialized because missing from the checkpoint. Consider training on your downstream task. generation_config.json: 0%| | 0.00/224 [00:00<?, ?B/s] generation_config.json: 100%|██████████| 224/224 [00:00<00:00, 734kB/s] preprocessor_config.json: 0%| | 0.00/369 [00:00<?, ?B/s] preprocessor_config.json: 100%|██████████| 369/369 [00:00<00:00, 1.61MB/s] Traceback (most recent call last): File "/app/app.py", line 10, in <module> processor = AutoProcessor.from_pretrained("facebook/musicgen-melody") File "/usr/local/lib/python3.13/site-packages/transformers/models/auto/processing_auto.py", line 396, in from_pretrained return processor_class.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/utils/import_utils.py", line 1946, in __getattribute__ requires_backends(cls, cls._backends) ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/utils/import_utils.py", line 1932, in requires_backends raise ImportError("".join(failed)) ImportError: MusicgenMelodyProcessor requires the torchaudio library but it was not found in your environment. Please install it and restart your runtime.

Container logs: