Error while running cli_inference.py

[Dipto084]

I am trying to run the inference code on a audio file with a text prompt, after I provide the wav_path and the prompt, I get this error -

spectrogram = wav_processor(audio, sampling_rate=sr, return_tensors="pt")["input_features"]
File "../SALMONN/salmonn_env/lib/python3.10/site-packages/transformers/models/whisper/feature_extraction_whisper.py", line 364, in call
padded_inputs = padded_inputs.convert_to_tensors(return_tensors)
File "../SALMONN/salmonn_env/lib/python3.10/site-packages/transformers/feature_extraction_utils.py", line 171, in convert_to_tensors
raise ValueError(
ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length.

I tried adding padding=True in the `spectrogram = wav_processor(audio, sampling_rate=sr, return_tensors="pt")["input_features"]' line, but does not help either, shows the same error