/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") 2023-10-10 20:14:56 | WARNING | root | Pytorch pre-release version 2.1.0.dev20230831+cu118 - assuming intent to test it /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_4196_encode {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_test_8x_400k_4196_encode 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: 7%|▋ | 245/3515 [00:00<00:01, 2443.91it/s] word -> phonemes: 14%|█▍ | 490/3515 [00:00<00:01, 2318.72it/s] word -> phonemes: 22%|██▏ | 758/3515 [00:00<00:01, 2478.33it/s] word -> phonemes: 29%|██▊ | 1007/3515 [00:00<00:01, 2322.16it/s] word -> phonemes: 37%|███▋ | 1317/3515 [00:00<00:00, 2586.07it/s] word -> phonemes: 47%|████▋ | 1640/3515 [00:00<00:00, 2795.41it/s] word -> phonemes: 56%|█████▌ | 1955/3515 [00:00<00:00, 2906.08it/s] word -> phonemes: 65%|██████▍ | 2282/3515 [00:00<00:00, 3018.34it/s] word -> phonemes: 74%|███████▎ | 2586/3515 [00:00<00:00, 2990.77it/s] word -> phonemes: 82%|████████▏ | 2887/3515 [00:01<00:00, 2632.24it/s] word -> phonemes: 91%|█████████ | 3191/3515 [00:01<00:00, 2744.35it/s] word -> phonemes: 99%|█████████▉| 3488/3515 [00:01<00:00, 2807.14it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2731.24it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 360/2703 [00:00<00:00, 3592.96it/s] word -> phonemes: 27%|██▋ | 724/2703 [00:00<00:00, 3616.62it/s] word -> phonemes: 40%|████ | 1093/2703 [00:00<00:00, 3648.02it/s] word -> phonemes: 54%|█████▍ | 1458/2703 [00:00<00:00, 3368.09it/s] word -> phonemes: 67%|██████▋ | 1798/2703 [00:00<00:00, 3263.67it/s] word -> phonemes: 80%|███████▉ | 2161/2703 [00:00<00:00, 3377.24it/s] word -> phonemes: 93%|█████████▎| 2501/2703 [00:00<00:00, 3382.74it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3427.16it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 339/2703 [00:00<00:00, 3389.42it/s] word -> phonemes: 25%|██▌ | 678/2703 [00:00<00:00, 3155.92it/s] word -> phonemes: 37%|███▋ | 995/2703 [00:00<00:01, 1652.69it/s] word -> phonemes: 50%|█████ | 1361/2703 [00:00<00:00, 2145.62it/s] word -> phonemes: 64%|██████▍ | 1730/2703 [00:00<00:00, 2545.87it/s] word -> phonemes: 75%|███████▌ | 2040/2703 [00:00<00:00, 2690.04it/s] word -> phonemes: 87%|████████▋ | 2349/2703 [00:00<00:00, 2779.81it/s] word -> phonemes: 99%|█████████▉| 2685/2703 [00:01<00:00, 2878.27it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2578.67it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 355/2703 [00:00<00:00, 3530.31it/s] word -> phonemes: 26%|██▌ | 709/2703 [00:00<00:00, 3441.30it/s] word -> phonemes: 39%|███▉ | 1054/2703 [00:00<00:00, 3198.32it/s] word -> phonemes: 51%|█████ | 1376/2703 [00:00<00:00, 3193.13it/s] word -> phonemes: 63%|██████▎ | 1697/2703 [00:00<00:00, 3196.52it/s] word -> phonemes: 76%|███████▌ | 2061/2703 [00:00<00:00, 3340.44it/s] word -> phonemes: 90%|█████████ | 2438/2703 [00:00<00:00, 3476.92it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3384.56it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 8%|▊ | 295/3515 [00:00<00:01, 2949.49it/s] word -> phonemes: 17%|█▋ | 590/3515 [00:00<00:01, 2640.37it/s] word -> phonemes: 24%|██▍ | 857/3515 [00:00<00:01, 2462.40it/s] word -> phonemes: 31%|███▏ | 1105/3515 [00:00<00:01, 2272.36it/s] word -> phonemes: 39%|███▉ | 1364/3515 [00:00<00:00, 2372.60it/s] word -> phonemes: 46%|████▌ | 1613/3515 [00:00<00:00, 2408.37it/s] word -> phonemes: 53%|█████▎ | 1856/3515 [00:00<00:00, 2386.29it/s] word -> phonemes: 60%|██████ | 2110/3515 [00:00<00:00, 2432.98it/s] word -> phonemes: 67%|██████▋ | 2355/3515 [00:00<00:00, 2407.09it/s] word -> phonemes: 74%|███████▍ | 2597/3515 [00:01<00:00, 2385.69it/s] word -> phonemes: 81%|████████ | 2837/3515 [00:01<00:00, 2386.44it/s] word -> phonemes: 88%|████████▊ | 3076/3515 [00:01<00:00, 2356.96it/s] word -> phonemes: 96%|█████████▌| 3376/3515 [00:01<00:00, 2544.06it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2467.29it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 296/2703 [00:00<00:00, 2957.63it/s] word -> phonemes: 22%|██▏ | 592/2703 [00:00<00:00, 2490.16it/s] word -> phonemes: 33%|███▎ | 891/2703 [00:00<00:00, 2690.25it/s] word -> phonemes: 44%|████▍ | 1186/2703 [00:00<00:00, 2751.52it/s] word -> phonemes: 54%|█████▍ | 1465/2703 [00:00<00:00, 2731.81it/s] word -> phonemes: 64%|██████▍ | 1741/2703 [00:00<00:00, 2603.57it/s] word -> phonemes: 74%|███████▍ | 2004/2703 [00:00<00:00, 2584.66it/s] word -> phonemes: 84%|████████▍ | 2276/2703 [00:00<00:00, 2623.24it/s] word -> phonemes: 94%|█████████▍| 2552/2703 [00:00<00:00, 2664.38it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2650.55it/s] dev: 0%| | 0/2703 [00:00