runtime error

B/s] model.bin: 48%|████▊ | 231M/484M [00:06<00:05, 43.8MB/s] model.bin: 50%|████▉ | 241M/484M [00:06<00:07, 32.3MB/s] model.bin: 54%|█████▍ | 262M/484M [00:07<00:05, 37.1MB/s] model.bin: 56%|█████▋ | 273M/484M [00:07<00:06, 34.8MB/s] model.bin: 59%|█████▊ | 283M/484M [00:07<00:05, 35.6MB/s] model.bin: 61%|██████ | 294M/484M [00:08<00:04, 41.2MB/s] model.bin: 63%|██████▎ | 304M/484M [00:08<00:04, 39.6MB/s] model.bin: 67%|██████▋ | 325M/484M [00:08<00:03, 42.1MB/s] model.bin: 69%|██████▉ | 336M/484M [00:08<00:03, 43.2MB/s] model.bin: 72%|███████▏ | 346M/484M [00:09<00:02, 49.7MB/s] model.bin: 74%|███████▎ | 357M/484M [00:09<00:02, 50.6MB/s] model.bin: 78%|███████▊ | 377M/484M [00:09<00:02, 48.5MB/s] model.bin: 80%|████████ | 388M/484M [00:10<00:02, 43.4MB/s] model.bin: 85%|████████▍ | 409M/484M [00:10<00:01, 47.9MB/s] model.bin: 87%|████████▋ | 419M/484M [00:11<00:01, 32.4MB/s] model.bin: 89%|████████▉ | 430M/484M [00:11<00:01, 38.1MB/s] model.bin: 91%|█████████ | 440M/484M [00:11<00:01, 36.7MB/s] model.bin: 93%|█████████▎| 451M/484M [00:12<00:01, 32.4MB/s] model.bin: 98%|█████████▊| 472M/484M [00:12<00:00, 29.0MB/s] model.bin: 100%|█████████▉| 482M/484M [00:13<00:00, 26.5MB/s] model.bin: 100%|██████████| 484M/484M [00:13<00:00, 36.2MB/s] Traceback (most recent call last): File "/home/user/app/app.py", line 34, in <module> model = WhisperModel(model_size, device="cuda", compute_type="float16") File "/home/user/.local/lib/python3.10/site-packages/faster_whisper/transcribe.py", line 128, in __init__ self.model = ctranslate2.models.Whisper( RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version

Container logs: