/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 00:58:05 | 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 {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_test_8x_400k_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: 8%|▊ | 276/3515 [00:00<00:01, 2757.58it/s] word -> phonemes: 16%|█▌ | 552/3515 [00:00<00:01, 2592.69it/s] word -> phonemes: 24%|██▍ | 850/3515 [00:00<00:00, 2761.23it/s] word -> phonemes: 33%|███▎ | 1149/3515 [00:00<00:00, 2847.40it/s] word -> phonemes: 41%|████ | 1435/3515 [00:00<00:00, 2523.43it/s] word -> phonemes: 48%|████▊ | 1694/3515 [00:00<00:00, 2302.74it/s] word -> phonemes: 55%|█████▍ | 1931/3515 [00:00<00:00, 2268.83it/s] word -> phonemes: 62%|██████▏ | 2162/3515 [00:00<00:00, 2160.77it/s] word -> phonemes: 68%|██████▊ | 2381/3515 [00:01<00:00, 1968.21it/s] word -> phonemes: 73%|███████▎ | 2582/3515 [00:01<00:00, 1958.71it/s] word -> phonemes: 79%|███████▉ | 2781/3515 [00:01<00:00, 1924.51it/s] word -> phonemes: 85%|████████▍ | 2975/3515 [00:01<00:00, 1822.36it/s] word -> phonemes: 91%|█████████ | 3198/3515 [00:01<00:00, 1932.48it/s] word -> phonemes: 99%|█████████▊| 3471/3515 [00:01<00:00, 2154.91it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2204.74it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|▉ | 260/2703 [00:00<00:00, 2597.69it/s] word -> phonemes: 21%|██▏ | 577/2703 [00:00<00:00, 2932.23it/s] word -> phonemes: 33%|███▎ | 902/2703 [00:00<00:00, 3073.23it/s] word -> phonemes: 45%|████▍ | 1210/2703 [00:00<00:00, 3006.86it/s] word -> phonemes: 56%|█████▌ | 1512/2703 [00:00<00:00, 3008.46it/s] word -> phonemes: 68%|██████▊ | 1845/2703 [00:00<00:00, 3115.72it/s] word -> phonemes: 80%|███████▉ | 2157/2703 [00:00<00:00, 2949.91it/s] word -> phonemes: 92%|█████████▏| 2474/2703 [00:00<00:00, 3014.52it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3005.22it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 294/2703 [00:00<00:00, 2931.47it/s] word -> phonemes: 22%|██▏ | 594/2703 [00:00<00:00, 2971.55it/s] word -> phonemes: 33%|███▎ | 892/2703 [00:00<00:01, 1483.68it/s] word -> phonemes: 43%|████▎ | 1174/2703 [00:00<00:00, 1810.74it/s] word -> phonemes: 55%|█████▍ | 1483/2703 [00:00<00:00, 2140.84it/s] word -> phonemes: 66%|██████▌ | 1772/2703 [00:00<00:00, 2341.79it/s] word -> phonemes: 78%|███████▊ | 2097/2703 [00:00<00:00, 2565.48it/s] word -> phonemes: 88%|████████▊ | 2386/2703 [00:01<00:00, 2654.91it/s] word -> phonemes: 99%|█████████▉| 2672/2703 [00:01<00:00, 2660.29it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2364.11it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 303/2703 [00:00<00:00, 3021.68it/s] word -> phonemes: 23%|██▎ | 614/2703 [00:00<00:00, 3069.08it/s] word -> phonemes: 34%|███▍ | 921/2703 [00:00<00:00, 2782.70it/s] word -> phonemes: 46%|████▌ | 1240/2703 [00:00<00:00, 2932.88it/s] word -> phonemes: 57%|█████▋ | 1549/2703 [00:00<00:00, 2987.14it/s] word -> phonemes: 70%|██████▉ | 1884/2703 [00:00<00:00, 3105.35it/s] word -> phonemes: 81%|████████▏ | 2197/2703 [00:00<00:00, 3089.89it/s] word -> phonemes: 93%|█████████▎| 2508/2703 [00:00<00:00, 2797.83it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2814.10it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 6%|▌ | 212/3515 [00:00<00:01, 2010.97it/s] word -> phonemes: 12%|█▏ | 414/3515 [00:00<00:01, 1969.41it/s] word -> phonemes: 18%|█▊ | 629/3515 [00:00<00:01, 2046.27it/s] word -> phonemes: 24%|██▎ | 834/3515 [00:00<00:01, 2031.80it/s] word -> phonemes: 30%|██▉ | 1038/3515 [00:00<00:01, 1903.19it/s] word -> phonemes: 35%|███▍ | 1230/3515 [00:00<00:01, 1854.92it/s] word -> phonemes: 41%|████ | 1446/3515 [00:00<00:01, 1947.81it/s] word -> phonemes: 48%|████▊ | 1672/3515 [00:00<00:00, 2028.58it/s] word -> phonemes: 54%|█████▍ | 1903/3515 [00:00<00:00, 2113.54it/s] word -> phonemes: 60%|██████ | 2125/3515 [00:01<00:00, 2145.56it/s] word -> phonemes: 67%|██████▋ | 2341/3515 [00:01<00:00, 2074.57it/s] word -> phonemes: 73%|███████▎ | 2550/3515 [00:01<00:00, 2021.35it/s] word -> phonemes: 80%|███████▉ | 2804/3515 [00:01<00:00, 2169.89it/s] word -> phonemes: 86%|████████▌ | 3023/3515 [00:01<00:00, 2023.95it/s] word -> phonemes: 92%|█████████▏| 3242/3515 [00:01<00:00, 2070.24it/s] word -> phonemes: 98%|█████████▊| 3452/3515 [00:01<00:00, 2026.72it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2016.79it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|▉ | 269/2703 [00:00<00:00, 2686.13it/s] word -> phonemes: 22%|██▏ | 586/2703 [00:00<00:00, 2968.44it/s] word -> phonemes: 33%|███▎ | 883/2703 [00:00<00:00, 2923.90it/s] word -> phonemes: 45%|████▍ | 1206/2703 [00:00<00:00, 3040.09it/s] word -> phonemes: 56%|█████▌ | 1511/2703 [00:00<00:00, 2739.47it/s] word -> phonemes: 68%|██████▊ | 1843/2703 [00:00<00:00, 2920.98it/s] word -> phonemes: 79%|███████▉ | 2140/2703 [00:00<00:00, 2885.97it/s] word -> phonemes: 91%|█████████ | 2463/2703 [00:00<00:00, 2989.75it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2877.34it/s] dev: 0%| | 0/2703 [00:00