Segmentation Fault when providing transcript

[AvivNavon]

Thank you for this great repo!
When following your readme example for generating audio with transcript, I get segmentation fault error.

The steps I took:

1. Starting a new conda env: conda create -n audioldm python=3.8
2. Activate env: conda activate audioldm
3. Install repo: pip3 install git+https://github.com/haoheliu/AudioLDM2.git
4. Running generation: audioldm2 -t "A female reporter is speaking" --transcription "Wish you have a good day"

Importantly, after removing the --transcript it works and I was able to generate audio only, but not audio + transcript.

[ZJSYo]

I also encountered the same problem. Have you solved it?