/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") 2023-09-25 14:26:29 | 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_test_5sec_att_relax_addmel {'model_config': None, 'refresh': False} Loading model from Local mert_test_5sec_att_relax_addmel 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: 5%|▍ | 167/3515 [00:00<00:02, 1660.24it/s] word -> phonemes: 10%|▉ | 334/3515 [00:00<00:02, 1585.86it/s] word -> phonemes: 14%|█▍ | 508/3515 [00:00<00:01, 1651.42it/s] word -> phonemes: 19%|█▉ | 683/3515 [00:00<00:01, 1688.98it/s] word -> phonemes: 24%|██▍ | 853/3515 [00:00<00:01, 1683.77it/s] word -> phonemes: 29%|██▉ | 1029/3515 [00:00<00:01, 1708.23it/s] word -> phonemes: 35%|███▍ | 1217/3515 [00:00<00:01, 1763.51it/s] word -> phonemes: 40%|███▉ | 1396/3515 [00:00<00:01, 1769.92it/s] word -> phonemes: 45%|████▍ | 1579/3515 [00:00<00:01, 1785.77it/s] word -> phonemes: 50%|█████ | 1758/3515 [00:01<00:01, 1734.89it/s] word -> phonemes: 55%|█████▍ | 1932/3515 [00:01<00:00, 1713.81it/s] word -> phonemes: 60%|██████ | 2118/3515 [00:01<00:00, 1755.95it/s] word -> phonemes: 65%|██████▌ | 2294/3515 [00:01<00:00, 1734.59it/s] word -> phonemes: 70%|███████ | 2468/3515 [00:01<00:00, 1656.60it/s] word -> phonemes: 75%|███████▌ | 2643/3515 [00:01<00:00, 1681.70it/s] word -> phonemes: 80%|████████ | 2817/3515 [00:01<00:00, 1697.20it/s] word -> phonemes: 85%|████████▌ | 2988/3515 [00:01<00:00, 1652.86it/s] word -> phonemes: 90%|████████▉ | 3154/3515 [00:01<00:00, 1646.61it/s] word -> phonemes: 94%|█████████▍| 3320/3515 [00:01<00:00, 1640.46it/s] word -> phonemes: 99%|█████████▉| 3485/3515 [00:02<00:00, 1616.65it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:02<00:00, 1687.06it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 7%|▋ | 188/2703 [00:00<00:01, 1877.78it/s] word -> phonemes: 14%|█▍ | 381/2703 [00:00<00:01, 1898.92it/s] word -> phonemes: 21%|██▏ | 579/2703 [00:00<00:01, 1933.97it/s] word -> phonemes: 29%|██▊ | 777/2703 [00:00<00:00, 1951.23it/s] word -> phonemes: 36%|███▌ | 977/2703 [00:00<00:00, 1965.47it/s] word -> phonemes: 43%|████▎ | 1174/2703 [00:00<00:00, 1882.92it/s] word -> phonemes: 51%|█████ | 1370/2703 [00:00<00:00, 1905.69it/s] word -> phonemes: 58%|█████▊ | 1565/2703 [00:00<00:00, 1916.97it/s] word -> phonemes: 66%|██████▌ | 1771/2703 [00:00<00:00, 1958.98it/s] word -> phonemes: 73%|███████▎ | 1970/2703 [00:01<00:00, 1964.34it/s] word -> phonemes: 81%|████████ | 2178/2703 [00:01<00:00, 1997.44it/s] word -> phonemes: 88%|████████▊ | 2378/2703 [00:01<00:00, 1954.16it/s] word -> phonemes: 95%|█████████▌| 2574/2703 [00:01<00:00, 1922.42it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 1934.02it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 220/2703 [00:00<00:01, 2196.70it/s] word -> phonemes: 16%|█▋ | 440/2703 [00:00<00:01, 2156.10it/s] word -> phonemes: 24%|██▍ | 656/2703 [00:00<00:00, 2125.06it/s] word -> phonemes: 32%|███▏ | 871/2703 [00:00<00:00, 2132.43it/s] word -> phonemes: 40%|████ | 1086/2703 [00:00<00:00, 2137.71it/s] word -> phonemes: 48%|████▊ | 1308/2703 [00:00<00:00, 2163.37it/s] word -> phonemes: 56%|█████▋ | 1525/2703 [00:00<00:00, 2160.88it/s] word -> phonemes: 64%|██████▍ | 1742/2703 [00:00<00:00, 2146.20it/s] word -> phonemes: 73%|███████▎ | 1961/2703 [00:00<00:00, 2156.42it/s] word -> phonemes: 81%|████████ | 2184/2703 [00:01<00:00, 2176.37it/s] word -> phonemes: 89%|████████▉ | 2402/2703 [00:01<00:00, 2112.34it/s] word -> phonemes: 97%|█████████▋| 2614/2703 [00:01<00:00, 2079.13it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2121.76it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 219/2703 [00:00<00:01, 2186.70it/s] word -> phonemes: 16%|█▌ | 438/2703 [00:00<00:01, 2059.40it/s] word -> phonemes: 24%|██▍ | 645/2703 [00:00<00:01, 2049.46it/s] word -> phonemes: 32%|███▏ | 855/2703 [00:00<00:00, 2066.39it/s] word -> phonemes: 39%|███▉ | 1067/2703 [00:00<00:00, 2083.14it/s] word -> phonemes: 47%|████▋ | 1281/2703 [00:00<00:00, 2101.51it/s] word -> phonemes: 55%|█████▌ | 1495/2703 [00:00<00:00, 2113.61it/s] word -> phonemes: 63%|██████▎ | 1711/2703 [00:00<00:00, 2127.25it/s] word -> phonemes: 72%|███████▏ | 1935/2703 [00:00<00:00, 2158.57it/s] word -> phonemes: 80%|███████▉ | 2151/2703 [00:01<00:00, 2153.27it/s] word -> phonemes: 88%|████████▊ | 2367/2703 [00:01<00:00, 2121.02it/s] word -> phonemes: 95%|█████████▌| 2580/2703 [00:01<00:00, 2096.62it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2099.30it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 5%|▌ | 181/3515 [00:00<00:01, 1802.61it/s] word -> phonemes: 10%|█ | 362/3515 [00:00<00:01, 1686.34it/s] word -> phonemes: 15%|█▌ | 538/3515 [00:00<00:01, 1718.09it/s] word -> phonemes: 21%|██ | 727/3515 [00:00<00:01, 1784.23it/s] word -> phonemes: 26%|██▌ | 909/3515 [00:00<00:01, 1793.67it/s] word -> phonemes: 31%|███ | 1098/3515 [00:00<00:01, 1824.33it/s] word -> phonemes: 37%|███▋ | 1291/3515 [00:00<00:01, 1857.90it/s] word -> phonemes: 42%|████▏ | 1479/3515 [00:00<00:01, 1862.36it/s] word -> phonemes: 47%|████▋ | 1666/3515 [00:00<00:01, 1838.27it/s] word -> phonemes: 53%|█████▎ | 1850/3515 [00:01<00:00, 1826.90it/s] word -> phonemes: 58%|█████▊ | 2037/3515 [00:01<00:00, 1838.77it/s] word -> phonemes: 63%|██████▎ | 2228/3515 [00:01<00:00, 1859.93it/s] word -> phonemes: 69%|██████▊ | 2415/3515 [00:01<00:00, 1760.76it/s] word -> phonemes: 74%|███████▍ | 2594/3515 [00:01<00:00, 1767.04it/s] word -> phonemes: 79%|███████▉ | 2776/3515 [00:01<00:00, 1779.42it/s] word -> phonemes: 84%|████████▍ | 2955/3515 [00:01<00:00, 1736.03it/s] word -> phonemes: 89%|████████▉ | 3130/3515 [00:01<00:00, 1708.32it/s] word -> phonemes: 94%|█████████▍| 3302/3515 [00:01<00:00, 1710.02it/s] word -> phonemes: 99%|█████████▉| 3474/3515 [00:01<00:00, 1682.49it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 1769.76it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 207/2703 [00:00<00:01, 2066.41it/s] word -> phonemes: 16%|█▌ | 419/2703 [00:00<00:01, 2095.72it/s] word -> phonemes: 23%|██▎ | 629/2703 [00:00<00:01, 2060.08it/s] word -> phonemes: 31%|███ | 836/2703 [00:00<00:00, 2062.67it/s] word -> phonemes: 39%|███▊ | 1045/2703 [00:00<00:00, 2071.23it/s] word -> phonemes: 46%|████▋ | 1253/2703 [00:00<00:00, 2069.89it/s] word -> phonemes: 54%|█████▍ | 1462/2703 [00:00<00:00, 2072.55it/s] word -> phonemes: 62%|██████▏ | 1680/2703 [00:00<00:00, 2104.78it/s] word -> phonemes: 70%|███████ | 1899/2703 [00:00<00:00, 2130.39it/s] word -> phonemes: 78%|███████▊ | 2113/2703 [00:01<00:00, 2092.18it/s] word -> phonemes: 86%|████████▌ | 2323/2703 [00:01<00:00, 2069.91it/s] word -> phonemes: 94%|█████████▎| 2531/2703 [00:01<00:00, 2036.30it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2056.52it/s] dev: 0%| | 0/2703 [00:00