search

TMElyralab / MuseTalk

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
Other
1.93k stars 235 forks source link

KeyError: 'encoder_embeddings' #1

Closed einsqing closed 3 months ago

einsqing commented 3 months ago

Traceback (most recent call last): File "/root/anaconda3/envs/musetalk/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/root/anaconda3/envs/musetalk/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/home/heqing/test/MuseTalk/scripts/inference.py", line 141, in main(args) File "/root/anaconda3/envs/musetalk/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/home/heqing/test/MuseTalk/scripts/inference.py", line 55, in main whisper_feature = audio_processor.audio2feat(audio_path) File "/home/heqing/test/MuseTalk/musetalk/whisper/audio2feature.py", line 99, in audio2feat encoder_embeddings = emb['encoder_embeddings'] KeyError: 'encoder_embeddings'

itechmusic commented 3 months ago

Hi there, are u running the example testcase or your own data?

Did you install our modified version of whisper using this command https://github.com/TMElyralab/MuseTalk?tab=readme-ov-file#whisper ?

Traceback (most recent call last): File "/root/anaconda3/envs/musetalk/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/root/anaconda3/envs/musetalk/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/home/heqing/test/MuseTalk/scripts/inference.py", line 141, in main(args) File "/root/anaconda3/envs/musetalk/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/home/heqing/test/MuseTalk/scripts/inference.py", line 55, in main whisper_feature = audio_processor.audio2feat(audio_path) File "/home/heqing/test/MuseTalk/musetalk/whisper/audio2feature.py", line 99, in audio2feat encoder_embeddings = emb['encoder_embeddings'] KeyError: 'encoder_embeddings'

itechmusic commented 3 months ago

We just updated the inference codes and README, so you don't need to pip install whisper now. Plz let me know if it helps.