/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") 2023-09-23 01:01:45 | 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_encode_norm {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_test_8x_400k_encode_norm 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%|▋ | 250/3515 [00:00<00:01, 2497.72it/s] word -> phonemes: 14%|█▍ | 500/3515 [00:00<00:01, 2054.62it/s] word -> phonemes: 20%|██ | 711/3515 [00:00<00:01, 1935.97it/s] word -> phonemes: 26%|██▌ | 908/3515 [00:00<00:01, 1861.35it/s] word -> phonemes: 32%|███▏ | 1108/3515 [00:00<00:01, 1905.67it/s] word -> phonemes: 37%|███▋ | 1300/3515 [00:00<00:01, 1901.02it/s] word -> phonemes: 44%|████▎ | 1531/3515 [00:00<00:00, 2027.54it/s] word -> phonemes: 50%|█████ | 1769/3515 [00:00<00:00, 2134.50it/s] word -> phonemes: 56%|█████▋ | 1984/3515 [00:00<00:00, 1992.62it/s] word -> phonemes: 63%|██████▎ | 2199/3515 [00:01<00:00, 2037.50it/s] word -> phonemes: 69%|██████▉ | 2432/3515 [00:01<00:00, 2120.99it/s] word -> phonemes: 76%|███████▌ | 2674/3515 [00:01<00:00, 2207.56it/s] word -> phonemes: 82%|████████▏ | 2897/3515 [00:01<00:00, 2177.75it/s] word -> phonemes: 89%|████████▉ | 3128/3515 [00:01<00:00, 2215.82it/s] word -> phonemes: 95%|█████████▌| 3351/3515 [00:01<00:00, 2182.74it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2074.93it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 223/2703 [00:00<00:01, 2228.12it/s] word -> phonemes: 17%|█▋ | 446/2703 [00:00<00:01, 1955.43it/s] word -> phonemes: 24%|██▍ | 644/2703 [00:00<00:01, 1658.58it/s] word -> phonemes: 32%|███▏ | 853/2703 [00:00<00:01, 1803.02it/s] word -> phonemes: 40%|████ | 1092/2703 [00:00<00:00, 1992.99it/s] word -> phonemes: 48%|████▊ | 1297/2703 [00:00<00:00, 1983.59it/s] word -> phonemes: 58%|█████▊ | 1566/2703 [00:00<00:00, 2201.78it/s] word -> phonemes: 68%|██████▊ | 1849/2703 [00:00<00:00, 2392.67it/s] word -> phonemes: 77%|███████▋ | 2092/2703 [00:00<00:00, 2352.77it/s] word -> phonemes: 89%|████████▊ | 2393/2703 [00:01<00:00, 2547.96it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2294.81it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 292/2703 [00:00<00:00, 2917.05it/s] word -> phonemes: 22%|██▏ | 584/2703 [00:00<00:00, 2460.23it/s] word -> phonemes: 31%|███ | 835/2703 [00:00<00:01, 1134.24it/s] word -> phonemes: 40%|███▉ | 1079/2703 [00:00<00:01, 1411.36it/s] word -> phonemes: 49%|████▉ | 1318/2703 [00:00<00:00, 1639.21it/s] word -> phonemes: 59%|█████▊ | 1587/2703 [00:00<00:00, 1901.22it/s] word -> phonemes: 71%|███████ | 1912/2703 [00:01<00:00, 2254.26it/s] word -> phonemes: 80%|████████ | 2174/2703 [00:01<00:00, 2327.63it/s] word -> phonemes: 90%|█████████ | 2433/2703 [00:01<00:00, 2296.40it/s] word -> phonemes: 99%|█████████▉| 2681/2703 [00:01<00:00, 2197.46it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 1965.42it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 322/2703 [00:00<00:00, 3218.12it/s] word -> phonemes: 24%|██▍ | 646/2703 [00:00<00:00, 3228.42it/s] word -> phonemes: 36%|███▌ | 969/2703 [00:00<00:00, 3016.44it/s] word -> phonemes: 47%|████▋ | 1273/2703 [00:00<00:00, 2981.36it/s] word -> phonemes: 58%|█████▊ | 1572/2703 [00:00<00:00, 2968.37it/s] word -> phonemes: 71%|███████ | 1910/2703 [00:00<00:00, 3102.53it/s] word -> phonemes: 82%|████████▏ | 2221/2703 [00:00<00:00, 3072.89it/s] word -> phonemes: 94%|█████████▎| 2529/2703 [00:00<00:00, 3064.84it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2979.61it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 6%|▌ | 206/3515 [00:00<00:01, 1984.78it/s] word -> phonemes: 12%|█▏ | 405/3515 [00:00<00:01, 1841.49it/s] word -> phonemes: 17%|█▋ | 594/3515 [00:00<00:01, 1850.44it/s] word -> phonemes: 22%|██▏ | 780/3515 [00:00<00:01, 1647.32it/s] word -> phonemes: 29%|██▊ | 1005/3515 [00:00<00:01, 1842.71it/s] word -> phonemes: 36%|███▌ | 1252/3515 [00:00<00:01, 2041.31it/s] word -> phonemes: 42%|████▏ | 1461/3515 [00:00<00:01, 1919.10it/s] word -> phonemes: 49%|████▊ | 1710/3515 [00:00<00:00, 2085.18it/s] word -> phonemes: 55%|█████▍ | 1923/3515 [00:00<00:00, 2058.89it/s] word -> phonemes: 63%|██████▎ | 2221/3515 [00:01<00:00, 2327.89it/s] word -> phonemes: 70%|██████▉ | 2458/3515 [00:01<00:00, 2246.47it/s] word -> phonemes: 78%|███████▊ | 2727/3515 [00:01<00:00, 2373.29it/s] word -> phonemes: 84%|████████▍ | 2967/3515 [00:01<00:00, 2279.85it/s] word -> phonemes: 91%|█████████ | 3206/3515 [00:01<00:00, 2308.93it/s] word -> phonemes: 99%|█████████▊| 3466/3515 [00:01<00:00, 2392.60it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2157.85it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 213/2703 [00:00<00:01, 2123.90it/s] word -> phonemes: 16%|█▌ | 426/2703 [00:00<00:01, 2110.21it/s] word -> phonemes: 24%|██▎ | 638/2703 [00:00<00:01, 2042.11it/s] word -> phonemes: 31%|███▏ | 851/2703 [00:00<00:00, 2074.41it/s] word -> phonemes: 40%|████ | 1090/2703 [00:00<00:00, 2183.31it/s] word -> phonemes: 48%|████▊ | 1309/2703 [00:00<00:00, 2172.05it/s] word -> phonemes: 56%|█████▋ | 1527/2703 [00:00<00:00, 2154.36it/s] word -> phonemes: 65%|██████▍ | 1745/2703 [00:00<00:00, 2161.34it/s] word -> phonemes: 73%|███████▎ | 1962/2703 [00:00<00:00, 2099.93it/s] word -> phonemes: 81%|████████ | 2183/2703 [00:01<00:00, 2131.64it/s] word -> phonemes: 89%|████████▊ | 2397/2703 [00:01<00:00, 2094.71it/s] word -> phonemes: 96%|█████████▋| 2607/2703 [00:01<00:00, 2080.29it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2105.31it/s] dev: 0%| | 0/2703 [00:00