RuntimeError: Pretrained weights not found for model HTSAT-base.

[glory20h]

Hello, thank you for sharing the model of your amazing work.

I wish to try out speech generation based on (1) the transcription and (2) the description of the speaker.

However, when I run audioldm2 -t "A female reporter is speaking full of emotion" --transcription "Wish you have a good day", I get an error,

RuntimeError: Pretrained weights (/mnt/bn/lqhaoheliu/exps/checkpoints/audioldm/2023_04_07_audioldm_clap_v2_yusong/music_speech_audioset_epoch_15_esc_89.98.pt) not found for model HTSAT-base.

What could I be doing wrong?

Many thanks,

[SuperiorDtj]

Comment out this line of code ：/mnt/bn/lqhaoheliu/exps/checkpoints/audioldm/2023_04_07_audioldm_clap_v2_yusong/music_speech_audioset_epoch_15_esc_89.98.pt

[KalimeroJr]

Comment out this line of code ：/mnt/bn/lqhaoheliu/exps/checkpoints/audioldm/2023_04_07_audioldm_clap_v2_yusong/music_speech_audioset_epoch_15_esc_89.98.pt

In which file does this line appear?

[ahmedosman2001]

Comment out this line of code ：/mnt/bn/lqhaoheliu/exps/checkpoints/audioldm/2023_04_07_audioldm_clap_v2_yusong/music_speech_audioset_epoch_15_esc_89.98.pt

In which file does this line appear?

The file name is utils.py If you installed AudioLDM2 with this command pip3 install git+https://github.com/haoheliu/AudioLDM2.git you can run this command to locate this file pip3 show AudioLDM2. This will display the path where AudioLDM2 is installed. You can change your directory to that path. For example, my path was "/usr/local/lib/python3.10/dist-packages/audioldm2".