[ASR] Распознаю грузинскую речь: audio.mp3 (53.3 с...

[ASR] Распознаю грузинскую речь: audio.mp3 (53.3 сек.)
Traceback (most recent call last):
File "C:\Users\mamo5\Downloads\georgian_to_russian\georgian_to_russian\main.py", line 283, in <module>
main()
~~~~^^
File "C:\Users\mamo5\Downloads\georgian_to_russian\georgian_to_russian\main.py", line 278, in main
process_file(path)
~~~~~~~~~~~~^^^^^^
File "C:\Users\mamo5\Downloads\georgian_to_russian\georgian_to_russian\main.py", line 254, in process_file
georgian = transcribe_georgian(path)
File "C:\Users\mamo5\Downloads\georgian_to_russian\georgian_to_russian\main.py", line 130, in transcribe_georgian
generated = model.generate(
input_features,
...<3 lines>...
repetition_penalty=1.15,
)
File "C:\Users\mamo5\AppData\Local\Programs\Python\Python313\Lib\site-packages\transformers\models\whisper\generation_whisper.py", line 836, in generate
self._set_max_new_tokens_and_length(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
config=self.config,
^^^^^^^^^^^^^^^^^^^
decoder_input_ids=decoder_input_ids,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
generation_config=generation_config,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "C:\Users\mamo5\AppData\Local\Programs\Python\Python313\Lib\site-packages\transformers\models\whisper\generation_whisper.py", line 1932, in _set_max_new_tokens_and_length
raise ValueError(
...<6 lines>...
)
ValueError: The length of decoder_input_ids, including special start tokens, prompt tokens, and previous tokens, is 1, and max_new_tokens is 448. Thus, the combined length of decoder_input_ids and max_new_tokens is: 449. This exceeds the max_target_positions of the Whisper model: 448. You should either reduce the length of your prompt, or reduce the value of max_new_tokens, so that their combined length is less than 448.
исправь ошибки и скинь новый фул проект