runtime error

Exit code: 1. Reason: Loading Microsoft SpeechT5 model... preprocessor_config.json: 0%| | 0.00/433 [00:00<?, ?B/s] preprocessor_config.json: 100%|██████████| 433/433 [00:00<00:00, 2.55MB/s] Traceback (most recent call last): File "/app/app.py", line 111, in <module> demo = main() File "/app/app.py", line 46, in main processor, model, vocoder = load_model() ~~~~~~~~~~^^ File "/app/app.py", line 9, in load_model processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts") File "/usr/local/lib/python3.13/site-packages/transformers/processing_utils.py", line 1394, in from_pretrained args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, **kwargs) File "/usr/local/lib/python3.13/site-packages/transformers/processing_utils.py", line 1453, in _get_arguments_from_pretrained args.append(attribute_class.from_pretrained(pretrained_model_name_or_path, **kwargs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/utils/import_utils.py", line 2157, in __getattribute__ requires_backends(cls, cls._backends) ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.13/site-packages/transformers/utils/import_utils.py", line 2143, in requires_backends raise ImportError("".join(failed)) ImportError: SpeechT5Tokenizer requires the SentencePiece library but it was not found in your environment. Check out the instructions on the installation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones that match your environment. Please note that you may need to restart your runtime after installation.

Container logs: