/home/tony/Work/glockenspiel/s3prl/s3prl/upstream/byol_s/byol_a/common.py:20: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call. torchaudio.set_audio_backend("sox_io") /home/tony/Work/glockenspiel/s3prl/s3prl/run_downstream.py:157: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call. torchaudio.set_audio_backend('sox_io') [Featurizer] - The selected feature hidden_states's downsample rate is 960 [Runner] - Start a new experiment mert_test_8x_400k {'model_config': None, 'refresh': False} Loading model from Local mert_test_8x_400k load local model succeed load local feat extractor Wav2Vec2FeatureExtractor { "do_normalize": false, "feature_extractor_type": "Wav2Vec2FeatureExtractor", "feature_size": 1, "padding_side": "right", "padding_value": 0, "return_attention_mask": true, "sampling_rate": 24000 } overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 13%|█▎ | 457/3515 [00:00<00:00, 4563.87it/s] word -> phonemes: 26%|██▌ | 914/3515 [00:00<00:00, 4539.71it/s] word -> phonemes: 40%|███▉ | 1404/3515 [00:00<00:00, 4702.49it/s] word -> phonemes: 53%|█████▎ | 1875/3515 [00:00<00:00, 4615.76it/s] word -> phonemes: 66%|██████▋ | 2337/3515 [00:00<00:00, 4585.45it/s] word -> phonemes: 80%|███████▉ | 2802/3515 [00:00<00:00, 4605.63it/s] word -> phonemes: 93%|█████████▎| 3263/3515 [00:00<00:00, 4377.58it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4494.50it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 16%|█▌ | 424/2703 [00:00<00:00, 4236.66it/s] word -> phonemes: 31%|███▏ | 850/2703 [00:00<00:00, 4164.09it/s] word -> phonemes: 51%|█████ | 1370/2703 [00:00<00:00, 4627.99it/s] word -> phonemes: 68%|██████▊ | 1834/2703 [00:00<00:00, 4398.80it/s] word -> phonemes: 85%|████████▌ | 2310/2703 [00:00<00:00, 4520.83it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4218.98it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▍ | 405/2703 [00:00<00:00, 4047.38it/s] word -> phonemes: 32%|███▏ | 864/2703 [00:00<00:00, 4364.32it/s] word -> phonemes: 48%|████▊ | 1301/2703 [00:00<00:00, 4293.00it/s] word -> phonemes: 64%|██████▍ | 1731/2703 [00:00<00:00, 4201.63it/s] word -> phonemes: 80%|███████▉ | 2152/2703 [00:00<00:00, 4135.91it/s] word -> phonemes: 96%|█████████▌| 2590/2703 [00:00<00:00, 4187.90it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4239.15it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 447/2703 [00:00<00:00, 4465.29it/s] word -> phonemes: 33%|███▎ | 894/2703 [00:00<00:00, 4194.78it/s] word -> phonemes: 50%|█████ | 1353/2703 [00:00<00:00, 4366.34it/s] word -> phonemes: 67%|██████▋ | 1815/2703 [00:00<00:00, 4463.37it/s] word -> phonemes: 84%|████████▎ | 2263/2703 [00:00<00:00, 4391.56it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4214.33it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4294.78it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 10%|█ | 366/3515 [00:00<00:00, 3655.72it/s] word -> phonemes: 23%|██▎ | 824/3515 [00:00<00:00, 4194.29it/s] word -> phonemes: 36%|███▌ | 1255/3515 [00:00<00:00, 4246.47it/s] word -> phonemes: 48%|████▊ | 1680/3515 [00:00<00:00, 4030.59it/s] word -> phonemes: 62%|██████▏ | 2169/3515 [00:00<00:00, 4329.79it/s] word -> phonemes: 74%|███████▍ | 2605/3515 [00:00<00:00, 4050.67it/s] word -> phonemes: 87%|████████▋ | 3063/3515 [00:00<00:00, 4210.61it/s] word -> phonemes: 100%|█████████▉| 3501/3515 [00:00<00:00, 4261.49it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4188.87it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▌ | 416/2703 [00:00<00:00, 4151.68it/s] word -> phonemes: 33%|███▎ | 897/2703 [00:00<00:00, 4537.71it/s] word -> phonemes: 50%|████▉ | 1351/2703 [00:00<00:00, 4383.26it/s] word -> phonemes: 70%|██████▉ | 1891/2703 [00:00<00:00, 4772.65it/s] word -> phonemes: 88%|████████▊ | 2370/2703 [00:00<00:00, 4533.30it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4503.73it/s] dev: 0%| | 0/2703 [00:00