runtime error

Exit code: 1. Reason: net/ - - - If you do (or think that you should) have SoX, double-check your path variables. 2026-05-07 16:00:35.893570510 [W:onnxruntime:Default, device_discovery.cc:164 DiscoverDevicesForPlatform] GPU device discovery failed: device_discovery.cc:89 ReadFileContents Failed to open file: "/sys/class/drm/card0/device/vendor" Traceback (most recent call last): File "/home/user/app/app.py", line 12, in <module> from qwen_tts import Qwen3TTSModel File "/home/user/app/qwen_tts/__init__.py", line 21, in <module> from .inference.qwen3_tts_model import Qwen3TTSModel, VoiceClonePromptItem File "/home/user/app/qwen_tts/inference/qwen3_tts_model.py", line 29, in <module> from ..core.models import Qwen3TTSConfig, Qwen3TTSForConditionalGeneration, Qwen3TTSProcessor File "/home/user/app/qwen_tts/core/__init__.py", line 17, in <module> from .tokenizer_25hz.modeling_qwen3_tts_tokenizer_v1 import Qwen3TTSTokenizerV1Model File "/home/user/app/qwen_tts/core/tokenizer_25hz/modeling_qwen3_tts_tokenizer_v1.py", line 33, in <module> from .vq.speech_vq import WhisperEncoderVQ, XVectorExtractor File "/home/user/app/qwen_tts/core/tokenizer_25hz/vq/speech_vq.py", line 24, in <module> import torchaudio.compliance.kaldi as kaldi File "/usr/local/lib/python3.10/site-packages/torchaudio/__init__.py", line 7, in <module> from . import _extension # noqa # usort: skip File "/usr/local/lib/python3.10/site-packages/torchaudio/_extension/__init__.py", line 30, in <module> _IS_TORCHAUDIO_EXT_AVAILABLE = _load_lib("_torchaudio") File "/usr/local/lib/python3.10/site-packages/torchaudio/_extension/utils.py", line 56, in _load_lib torch.ops.load_library(paths[0]) File "/usr/local/lib/python3.10/site-packages/torch/_ops.py", line 1478, in load_library ctypes.CDLL(path) File "/usr/local/lib/python3.10/ctypes/__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) OSError: libcudart.so.13: cannot open shared object file: No such file or directory

Container logs: