/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") 2023-10-10 19:43:51 | 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_4196_encode_norm2 {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_test_8x_400k_4196_encode_norm2 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: 9%|▉ | 310/3515 [00:00<00:01, 3091.56it/s] word -> phonemes: 18%|█▊ | 620/3515 [00:00<00:00, 2941.69it/s] word -> phonemes: 27%|██▋ | 937/3515 [00:00<00:00, 3042.46it/s] word -> phonemes: 35%|███▌ | 1242/3515 [00:00<00:00, 2942.65it/s] word -> phonemes: 45%|████▍ | 1571/3515 [00:00<00:00, 3059.72it/s] word -> phonemes: 53%|█████▎ | 1878/3515 [00:00<00:00, 2948.77it/s] word -> phonemes: 63%|██████▎ | 2202/3515 [00:00<00:00, 3037.85it/s] word -> phonemes: 71%|███████▏ | 2507/3515 [00:00<00:00, 2916.66it/s] word -> phonemes: 80%|████████ | 2817/3515 [00:00<00:00, 2969.99it/s] word -> phonemes: 89%|████████▊ | 3116/3515 [00:01<00:00, 2909.97it/s] word -> phonemes: 98%|█████████▊| 3429/3515 [00:01<00:00, 2972.47it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2981.25it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 283/2703 [00:00<00:00, 2826.61it/s] word -> phonemes: 21%|██ | 566/2703 [00:00<00:00, 2825.27it/s] word -> phonemes: 32%|███▏ | 874/2703 [00:00<00:00, 2940.71it/s] word -> phonemes: 43%|████▎ | 1169/2703 [00:00<00:00, 2934.85it/s] word -> phonemes: 55%|█████▍ | 1478/2703 [00:00<00:00, 2988.62it/s] word -> phonemes: 66%|██████▌ | 1777/2703 [00:00<00:00, 2982.97it/s] word -> phonemes: 77%|███████▋ | 2085/2703 [00:00<00:00, 3012.98it/s] word -> phonemes: 88%|████████▊ | 2387/2703 [00:00<00:00, 2989.30it/s] word -> phonemes: 99%|█████████▉| 2686/2703 [00:00<00:00, 2936.38it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2943.49it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 291/2703 [00:00<00:00, 2906.39it/s] word -> phonemes: 22%|██▏ | 582/2703 [00:00<00:00, 2841.12it/s] word -> phonemes: 32%|███▏ | 867/2703 [00:00<00:00, 2821.71it/s] word -> phonemes: 43%|████▎ | 1166/2703 [00:00<00:00, 2883.33it/s] word -> phonemes: 54%|█████▍ | 1471/2703 [00:00<00:00, 1518.93it/s] word -> phonemes: 65%|██████▍ | 1756/2703 [00:00<00:00, 1795.56it/s] word -> phonemes: 75%|███████▌ | 2036/2703 [00:00<00:00, 2024.51it/s] word -> phonemes: 86%|████████▌ | 2315/2703 [00:01<00:00, 2207.80it/s] word -> phonemes: 95%|█████████▌| 2581/2703 [00:01<00:00, 2323.35it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2215.29it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 286/2703 [00:00<00:00, 2858.63it/s] word -> phonemes: 21%|██ | 572/2703 [00:00<00:00, 2639.85it/s] word -> phonemes: 31%|███▏ | 851/2703 [00:00<00:00, 2703.47it/s] word -> phonemes: 42%|████▏ | 1127/2703 [00:00<00:00, 2722.64it/s] word -> phonemes: 52%|█████▏ | 1406/2703 [00:00<00:00, 2746.39it/s] word -> phonemes: 63%|██████▎ | 1699/2703 [00:00<00:00, 2805.63it/s] word -> phonemes: 73%|███████▎ | 1980/2703 [00:00<00:00, 2783.65it/s] word -> phonemes: 84%|████████▎ | 2259/2703 [00:00<00:00, 2771.12it/s] word -> phonemes: 94%|█████████▍| 2537/2703 [00:00<00:00, 2687.85it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2741.52it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 7%|▋ | 242/3515 [00:00<00:01, 2418.38it/s] word -> phonemes: 14%|█▍ | 484/3515 [00:00<00:01, 2218.54it/s] word -> phonemes: 20%|██ | 714/3515 [00:00<00:01, 2252.91it/s] word -> phonemes: 27%|██▋ | 941/3515 [00:00<00:01, 2259.27it/s] word -> phonemes: 34%|███▍ | 1188/3515 [00:00<00:00, 2331.97it/s] word -> phonemes: 41%|████ | 1440/3515 [00:00<00:00, 2393.47it/s] word -> phonemes: 48%|████▊ | 1682/3515 [00:00<00:00, 2400.53it/s] word -> phonemes: 55%|█████▍ | 1926/3515 [00:00<00:00, 2412.99it/s] word -> phonemes: 62%|██████▏ | 2178/3515 [00:00<00:00, 2443.88it/s] word -> phonemes: 69%|██████▉ | 2423/3515 [00:01<00:00, 2445.12it/s] word -> phonemes: 76%|███████▌ | 2668/3515 [00:01<00:00, 2436.08it/s] word -> phonemes: 83%|████████▎ | 2932/3515 [00:01<00:00, 2492.53it/s] word -> phonemes: 91%|█████████ | 3182/3515 [00:01<00:00, 2482.42it/s] word -> phonemes: 98%|█████████▊| 3438/3515 [00:01<00:00, 2505.44it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2416.43it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 278/2703 [00:00<00:00, 2779.09it/s] word -> phonemes: 21%|██ | 556/2703 [00:00<00:00, 2690.82it/s] word -> phonemes: 31%|███ | 826/2703 [00:00<00:00, 2685.08it/s] word -> phonemes: 41%|████ | 1110/2703 [00:00<00:00, 2744.73it/s] word -> phonemes: 51%|█████▏ | 1387/2703 [00:00<00:00, 2752.06it/s] word -> phonemes: 62%|██████▏ | 1665/2703 [00:00<00:00, 2755.56it/s] word -> phonemes: 72%|███████▏ | 1954/2703 [00:00<00:00, 2797.39it/s] word -> phonemes: 83%|████████▎ | 2234/2703 [00:00<00:00, 2795.32it/s] word -> phonemes: 93%|█████████▎| 2514/2703 [00:00<00:00, 2707.40it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2700.82it/s] dev: 0%| | 0/2703 [00:00