/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") 2023-10-04 02:51:56 | 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] - 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 {'model_config': None, 'refresh': False} Loading model from Local mert_25hz_2nd_iter 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%|▋ | 229/3515 [00:00<00:01, 2216.19it/s] word -> phonemes: 13%|█▎ | 451/3515 [00:00<00:01, 1811.76it/s] word -> phonemes: 19%|█▉ | 670/3515 [00:00<00:01, 1963.10it/s] word -> phonemes: 25%|██▌ | 891/3515 [00:00<00:01, 2052.61it/s] word -> phonemes: 31%|███▏ | 1100/3515 [00:00<00:01, 1937.13it/s] word -> phonemes: 38%|███▊ | 1333/3515 [00:00<00:01, 2044.41it/s] word -> phonemes: 44%|████▍ | 1564/3515 [00:00<00:00, 2095.72it/s] word -> phonemes: 51%|█████ | 1776/3515 [00:00<00:00, 2087.54it/s] word -> phonemes: 57%|█████▋ | 1999/3515 [00:00<00:00, 2128.44it/s] word -> phonemes: 63%|██████▎ | 2216/3515 [00:01<00:00, 2137.79it/s] word -> phonemes: 69%|██████▉ | 2431/3515 [00:01<00:00, 1841.92it/s] word -> phonemes: 76%|███████▌ | 2672/3515 [00:01<00:00, 1994.70it/s] word -> phonemes: 82%|████████▏ | 2879/3515 [00:01<00:00, 1922.03it/s] word -> phonemes: 88%|████████▊ | 3085/3515 [00:01<00:00, 1958.49it/s] word -> phonemes: 95%|█████████▍| 3325/3515 [00:01<00:00, 2081.67it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2034.30it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 9%|▊ | 235/2703 [00:00<00:01, 2347.18it/s] word -> phonemes: 17%|█▋ | 470/2703 [00:00<00:00, 2323.15it/s] word -> phonemes: 26%|██▌ | 703/2703 [00:00<00:00, 2202.85it/s] word -> phonemes: 34%|███▍ | 924/2703 [00:00<00:00, 2147.08it/s] word -> phonemes: 42%|████▏ | 1140/2703 [00:00<00:00, 2062.88it/s] word -> phonemes: 50%|█████ | 1364/2703 [00:00<00:00, 2116.54it/s] word -> phonemes: 59%|█████▉ | 1597/2703 [00:00<00:00, 2182.67it/s] word -> phonemes: 67%|██████▋ | 1816/2703 [00:00<00:00, 2098.96it/s] word -> phonemes: 76%|███████▌ | 2051/2703 [00:00<00:00, 2173.84it/s] word -> phonemes: 84%|████████▍ | 2280/2703 [00:01<00:00, 2208.29it/s] word -> phonemes: 93%|█████████▎| 2517/2703 [00:01<00:00, 2255.84it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2172.07it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 294/2703 [00:00<00:00, 2936.47it/s] word -> phonemes: 22%|██▏ | 588/2703 [00:00<00:00, 2747.68it/s] word -> phonemes: 33%|███▎ | 897/2703 [00:00<00:00, 2896.05it/s] word -> phonemes: 44%|████▍ | 1188/2703 [00:00<00:00, 2596.55it/s] word -> phonemes: 54%|█████▎ | 1452/2703 [00:00<00:00, 2436.25it/s] word -> phonemes: 64%|██████▍ | 1739/2703 [00:00<00:00, 2568.77it/s] word -> phonemes: 76%|███████▌ | 2054/2703 [00:00<00:00, 2743.80it/s] word -> phonemes: 86%|████████▋ | 2333/2703 [00:00<00:00, 2662.16it/s] word -> phonemes: 96%|█████████▋| 2603/2703 [00:00<00:00, 2646.71it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2644.90it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|▉ | 264/2703 [00:00<00:00, 2636.90it/s] word -> phonemes: 21%|██ | 558/2703 [00:00<00:00, 2812.01it/s] word -> phonemes: 31%|███ | 840/2703 [00:00<00:00, 2676.76it/s] word -> phonemes: 41%|████ | 1111/2703 [00:00<00:00, 2688.50it/s] word -> phonemes: 51%|█████ | 1381/2703 [00:00<00:00, 2660.13it/s] word -> phonemes: 62%|██████▏ | 1672/2703 [00:00<00:00, 2742.44it/s] word -> phonemes: 73%|███████▎ | 1962/2703 [00:00<00:00, 2790.26it/s] word -> phonemes: 83%|████████▎ | 2249/2703 [00:00<00:00, 2813.61it/s] word -> phonemes: 94%|█████████▍| 2536/2703 [00:00<00:00, 2829.84it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2776.82it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 7%|▋ | 256/3515 [00:00<00:01, 2555.65it/s] word -> phonemes: 15%|█▍ | 512/3515 [00:00<00:01, 2416.48it/s] word -> phonemes: 22%|██▏ | 771/3515 [00:00<00:01, 2492.61it/s] word -> phonemes: 29%|██▉ | 1023/3515 [00:00<00:00, 2500.00it/s] word -> phonemes: 37%|███▋ | 1299/3515 [00:00<00:00, 2589.69it/s] word -> phonemes: 45%|████▍ | 1566/3515 [00:00<00:00, 2614.82it/s] word -> phonemes: 52%|█████▏ | 1837/3515 [00:00<00:00, 2645.16it/s] word -> phonemes: 60%|█████▉ | 2102/3515 [00:00<00:00, 2593.06it/s] word -> phonemes: 67%|██████▋ | 2368/3515 [00:00<00:00, 2612.82it/s] word -> phonemes: 75%|███████▌ | 2642/3515 [00:01<00:00, 2648.73it/s] word -> phonemes: 83%|████████▎ | 2908/3515 [00:01<00:00, 2577.40it/s] word -> phonemes: 90%|█████████ | 3175/3515 [00:01<00:00, 2602.71it/s] word -> phonemes: 98%|█████████▊| 3436/3515 [00:01<00:00, 2562.25it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2579.94it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 285/2703 [00:00<00:00, 2846.61it/s] word -> phonemes: 21%|██ | 570/2703 [00:00<00:00, 2619.52it/s] word -> phonemes: 32%|███▏ | 871/2703 [00:00<00:00, 2788.69it/s] word -> phonemes: 43%|████▎ | 1152/2703 [00:00<00:00, 2693.53it/s] word -> phonemes: 53%|█████▎ | 1423/2703 [00:00<00:00, 2435.75it/s] word -> phonemes: 62%|██████▏ | 1671/2703 [00:00<00:00, 2393.12it/s] word -> phonemes: 73%|███████▎ | 1978/2703 [00:00<00:00, 2595.46it/s] word -> phonemes: 83%|████████▎ | 2253/2703 [00:00<00:00, 2640.83it/s] word -> phonemes: 95%|█████████▍| 2560/2703 [00:00<00:00, 2767.84it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2670.13it/s] dev: 0%| | 0/2703 [00:00