/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") 2023-10-05 19:45:39 | 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] - Take a list of 13 features and weighted sum them. [Featurizer] - The selected feature hidden_states's downsample rate is 960 [Runner] - Start a new experiment mert_25hz_2nd_iter_1x {'model_config': None, 'refresh': False} Loading model from Local mert_25hz_2nd_iter_1x 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: 4%|▍ | 154/3515 [00:00<00:02, 1538.54it/s] word -> phonemes: 11%|█▏ | 404/3515 [00:00<00:01, 2099.49it/s] word -> phonemes: 19%|█▊ | 653/3515 [00:00<00:01, 2273.41it/s] word -> phonemes: 26%|██▌ | 904/3515 [00:00<00:01, 2365.32it/s] word -> phonemes: 33%|███▎ | 1149/3515 [00:00<00:00, 2393.91it/s] word -> phonemes: 40%|███▉ | 1389/3515 [00:00<00:00, 2387.73it/s] word -> phonemes: 47%|████▋ | 1637/3515 [00:00<00:00, 2416.78it/s] word -> phonemes: 53%|█████▎ | 1879/3515 [00:00<00:00, 2293.24it/s] word -> phonemes: 61%|██████ | 2139/3515 [00:00<00:00, 2383.29it/s] word -> phonemes: 68%|██████▊ | 2379/3515 [00:01<00:00, 2243.35it/s] word -> phonemes: 74%|███████▍ | 2606/3515 [00:01<00:00, 2226.91it/s] word -> phonemes: 81%|████████ | 2831/3515 [00:01<00:00, 2175.53it/s] word -> phonemes: 88%|████████▊ | 3091/3515 [00:01<00:00, 2296.27it/s] word -> phonemes: 95%|█████████▌| 3347/3515 [00:01<00:00, 2370.30it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2232.34it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 203/2703 [00:00<00:01, 2023.96it/s] word -> phonemes: 17%|█▋ | 451/2703 [00:00<00:00, 2291.57it/s] word -> phonemes: 26%|██▌ | 693/2703 [00:00<00:00, 2349.00it/s] word -> phonemes: 35%|███▌ | 959/2703 [00:00<00:00, 2470.44it/s] word -> phonemes: 45%|████▍ | 1215/2703 [00:00<00:00, 2497.08it/s] word -> phonemes: 54%|█████▍ | 1465/2703 [00:00<00:00, 2430.54it/s] word -> phonemes: 64%|██████▎ | 1723/2703 [00:00<00:00, 2478.15it/s] word -> phonemes: 73%|███████▎ | 1972/2703 [00:00<00:00, 2331.96it/s] word -> phonemes: 82%|████████▏ | 2226/2703 [00:00<00:00, 2391.69it/s] word -> phonemes: 92%|█████████▏| 2492/2703 [00:01<00:00, 2470.05it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2435.92it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█▏ | 310/2703 [00:00<00:00, 3092.67it/s] word -> phonemes: 23%|██▎ | 620/2703 [00:00<00:00, 3087.64it/s] word -> phonemes: 35%|███▍ | 936/2703 [00:00<00:00, 3118.24it/s] word -> phonemes: 46%|████▌ | 1248/2703 [00:00<00:00, 2912.79it/s] word -> phonemes: 57%|█████▋ | 1542/2703 [00:00<00:00, 2424.79it/s] word -> phonemes: 66%|██████▋ | 1796/2703 [00:00<00:00, 2349.86it/s] word -> phonemes: 75%|███████▌ | 2039/2703 [00:00<00:00, 2254.50it/s] word -> phonemes: 84%|████████▍ | 2270/2703 [00:00<00:00, 2208.22it/s] word -> phonemes: 92%|█████████▏| 2494/2703 [00:01<00:00, 2132.32it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2340.05it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 215/2703 [00:00<00:01, 2147.21it/s] word -> phonemes: 16%|█▋ | 443/2703 [00:00<00:01, 2222.65it/s] word -> phonemes: 25%|██▍ | 666/2703 [00:00<00:00, 2122.03it/s] word -> phonemes: 33%|███▎ | 879/2703 [00:00<00:00, 2086.42it/s] word -> phonemes: 40%|████ | 1088/2703 [00:00<00:00, 1908.89it/s] word -> phonemes: 48%|████▊ | 1292/2703 [00:00<00:00, 1949.24it/s] word -> phonemes: 56%|█████▌ | 1503/2703 [00:00<00:00, 1998.85it/s] word -> phonemes: 63%|██████▎ | 1710/2703 [00:00<00:00, 2019.72it/s] word -> phonemes: 73%|███████▎ | 1974/2703 [00:00<00:00, 2206.54it/s] word -> phonemes: 84%|████████▍ | 2280/2703 [00:01<00:00, 2464.90it/s] word -> phonemes: 94%|█████████▍| 2554/2703 [00:01<00:00, 2545.49it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2215.31it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 7%|▋ | 249/3515 [00:00<00:01, 2488.67it/s] word -> phonemes: 14%|█▍ | 498/3515 [00:00<00:01, 2414.89it/s] word -> phonemes: 22%|██▏ | 773/3515 [00:00<00:01, 2560.73it/s] word -> phonemes: 30%|██▉ | 1044/3515 [00:00<00:00, 2618.75it/s] word -> phonemes: 37%|███▋ | 1307/3515 [00:00<00:00, 2599.25it/s] word -> phonemes: 45%|████▍ | 1568/3515 [00:00<00:00, 2590.72it/s] word -> phonemes: 52%|█████▏ | 1828/3515 [00:00<00:00, 2570.25it/s] word -> phonemes: 60%|█████▉ | 2105/3515 [00:00<00:00, 2630.69it/s] word -> phonemes: 67%|██████▋ | 2369/3515 [00:00<00:00, 2544.32it/s] word -> phonemes: 75%|███████▌ | 2642/3515 [00:01<00:00, 2597.97it/s] word -> phonemes: 83%|████████▎ | 2903/3515 [00:01<00:00, 2597.98it/s] word -> phonemes: 90%|█████████ | 3164/3515 [00:01<00:00, 2413.20it/s] word -> phonemes: 97%|█████████▋| 3426/3515 [00:01<00:00, 2470.08it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2540.86it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 290/2703 [00:00<00:00, 2891.89it/s] word -> phonemes: 21%|██▏ | 580/2703 [00:00<00:00, 2799.49it/s] word -> phonemes: 33%|███▎ | 887/2703 [00:00<00:00, 2918.50it/s] word -> phonemes: 44%|████▍ | 1184/2703 [00:00<00:00, 2892.33it/s] word -> phonemes: 55%|█████▍ | 1474/2703 [00:00<00:00, 2701.79it/s] word -> phonemes: 65%|██████▍ | 1747/2703 [00:00<00:00, 2574.23it/s] word -> phonemes: 74%|███████▍ | 2007/2703 [00:00<00:00, 2440.34it/s] word -> phonemes: 83%|████████▎ | 2253/2703 [00:00<00:00, 2364.61it/s] word -> phonemes: 92%|█████████▏| 2491/2703 [00:00<00:00, 2342.06it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2537.20it/s] dev: 0%| | 0/2703 [00:00