Sample Results From Fastest Multimodal Model Around!!

#1
by awacke1 - opened

Image Results after uploading image.

aaronwacker_piano_Am_chord_key_markers_06e7b242-b16c-4294-8e5b-dec7c3ab74fc.png

image.png

Text Results

image.png

Audio Results

image.png

Video Results

image.png

This comment has been hidden

AttributeError:“NoneType”对象没有属性“write_audiofile”
追踪:
File "/usr/local/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 535, in _run_script
exec(code, module.dict)
File "/home/user/app/app.py", line 1749, in
main()
File "/home/user/app/app.py", line 1696, in main
process_audio_and_video(video_input)
File "/home/user/app/app.py", line 1650, in process_audio_and_video
base64Frames, audio_path = process_video(video_path, seconds_per_frame=1)
File "/home/user/app/app.py", line 1635, in process_video
clip.audio.write_audiofile(audio_path, bitrate="32k")

Sign up or log in to comment