runtime error

Exit code: 1. Reason: 70%|██████▉ | 3.49G/4.99G [00:04<00:01, 968MB/s] model-00003-of-00004.safetensors: 93%|█████████▎| 4.65G/4.99G [00:05<00:00, 1.03GB/s] model-00003-of-00004.safetensors: 100%|██████████| 4.99G/4.99G [00:06<00:00, 752MB/s] Downloading shards: 75%|███████▌ | 3/4 [00:17<00:06, 6.00s/it] model-00004-of-00004.safetensors: 0%| | 0.00/1.78G [00:00<?, ?B/s] model-00004-of-00004.safetensors: 4%|▍ | 67.7M/1.78G [00:01<00:29, 57.3MB/s] model-00004-of-00004.safetensors: 92%|█████████▏| 1.65G/1.78G [00:02<00:00, 865MB/s]  model-00004-of-00004.safetensors: 100%|██████████| 1.78G/1.78G [00:02<00:00, 760MB/s] Downloading shards: 100%|██████████| 4/4 [00:19<00:00, 4.57s/it] Downloading shards: 100%|██████████| 4/4 [00:19<00:00, 4.96s/it] Sliding Window Attention is enabled but not implemented for `sdpa`; unexpected results may be encountered. Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.97it/s] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.79it/s] Loading checkpoint shards: 100%|██████████| 4/4 [00:02<00:00, 1.81it/s] Traceback (most recent call last): File "/home/user/app/app.py", line 46, in <module> TOKEN2WAV = Token2wav(f"{MODEL_PATH}/token2wav") # load on CPU File "/home/user/app/token2wav.py", line 19, in __init__ self.audio_tokenizer = s3tokenizer.load_model(f"{model_path}/speech_tokenizer_v2_25hz.onnx").cuda().eval() File "/usr/local/lib/python3.10/site-packages/s3tokenizer/__init__.py", line 145, in load_model raise RuntimeError( RuntimeError: Model stepfun-ai/Step-Audio-2-mini/token2wav/speech_tokenizer_v2_25hz.onnx not found; available models = ['speech_tokenizer_v1', 'speech_tokenizer_v1_25hz', 'speech_tokenizer_v2_25hz']

Container logs: