ddlBoJack / emotion2vec

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
638 stars 47 forks source link

extract_features AssertionError #44

Open okmoments opened 2 months ago

okmoments commented 2 months ago

Traceback (most recent call last): File "/mnt/XXL/emotion2vec-large/scripts/extract_features.py", line 70, in main() File "/mnt/XXL/emotion2vec-large/scripts/extract_features.py", line 39, in main model, cfg, task = fairseq.checkpoint_utils.load_model_ensemble_and_task([checkpoint_dir]) File "/mnt/XXL/env/emotion2vec/lib/python3.9/site-packages/fairseq/checkpoint_utils.py", line 436, in load_model_ensemble_and_task task = tasks.setup_task(cfg.task) File "/mnt/XXL/env/emotion2vec/lib/python3.9/site-packages/fairseq/tasks/init.py", line 42, in setup_task assert ( AssertionError: Could not infer task type from {'_name': 'd2v_audio_classification', 'data': '/data/volume1/gaochangfeng.gcf/project/emo/fairseq_pai/examples/emo2vec/manifest/emo_box_fix', 'labels': 'lbl', ...

Is there any mismatch of code env? fairseq=0.12.2, torch=1.13.1

ddlBoJack commented 2 months ago

please follow the instruction to extract the features