/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 19:23:20 | 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: 6%|▋ | 220/3515 [00:00<00:01, 2188.44it/s] word -> phonemes: 13%|█▎ | 453/3515 [00:00<00:01, 2271.32it/s] word -> phonemes: 19%|█▉ | 685/3515 [00:00<00:01, 2293.38it/s] word -> phonemes: 26%|██▌ | 915/3515 [00:00<00:01, 2222.62it/s] word -> phonemes: 32%|███▏ | 1138/3515 [00:00<00:01, 2136.14it/s] word -> phonemes: 39%|███▊ | 1357/3515 [00:00<00:01, 2150.31it/s] word -> phonemes: 45%|████▌ | 1598/3515 [00:00<00:00, 2231.95it/s] word -> phonemes: 52%|█████▏ | 1822/3515 [00:00<00:00, 2223.04it/s] word -> phonemes: 58%|█████▊ | 2045/3515 [00:00<00:00, 2139.87it/s] word -> phonemes: 65%|██████▍ | 2281/3515 [00:01<00:00, 2204.95it/s] word -> phonemes: 71%|███████ | 2503/3515 [00:01<00:00, 1986.69it/s] word -> phonemes: 77%|███████▋ | 2706/3515 [00:01<00:00, 1924.39it/s] word -> phonemes: 83%|████████▎ | 2902/3515 [00:01<00:00, 1828.22it/s] word -> phonemes: 88%|████████▊ | 3088/3515 [00:01<00:00, 1757.09it/s] word -> phonemes: 94%|█████████▍| 3316/3515 [00:01<00:00, 1896.04it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2051.67it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 334/2703 [00:00<00:00, 3322.73it/s] word -> phonemes: 25%|██▍ | 667/2703 [00:00<00:00, 2700.96it/s] word -> phonemes: 37%|███▋ | 995/2703 [00:00<00:00, 2933.52it/s] word -> phonemes: 48%|████▊ | 1296/2703 [00:00<00:00, 2761.40it/s] word -> phonemes: 58%|█████▊ | 1577/2703 [00:00<00:00, 2739.59it/s] word -> phonemes: 70%|██████▉ | 1889/2703 [00:00<00:00, 2858.24it/s] word -> phonemes: 81%|████████ | 2178/2703 [00:00<00:00, 2847.36it/s] word -> phonemes: 91%|█████████ | 2465/2703 [00:00<00:00, 2715.49it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2821.93it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 14%|█▎ | 365/2703 [00:00<00:00, 3633.40it/s] word -> phonemes: 27%|██▋ | 729/2703 [00:00<00:00, 2940.05it/s] word -> phonemes: 38%|███▊ | 1034/2703 [00:00<00:00, 2981.22it/s] word -> phonemes: 51%|█████ | 1373/2703 [00:00<00:00, 3130.56it/s] word -> phonemes: 63%|██████▎ | 1691/2703 [00:00<00:00, 1412.78it/s] word -> phonemes: 76%|███████▌ | 2048/2703 [00:00<00:00, 1801.69it/s] word -> phonemes: 88%|████████▊ | 2384/2703 [00:01<00:00, 2120.53it/s] word -> phonemes: 99%|█████████▉| 2677/2703 [00:01<00:00, 2303.49it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2239.27it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 317/2703 [00:00<00:00, 3166.26it/s] word -> phonemes: 23%|██▎ | 634/2703 [00:00<00:00, 2850.25it/s] word -> phonemes: 36%|███▌ | 966/2703 [00:00<00:00, 3048.75it/s] word -> phonemes: 49%|████▊ | 1311/2703 [00:00<00:00, 3199.33it/s] word -> phonemes: 60%|██████ | 1633/2703 [00:00<00:00, 2957.28it/s] word -> phonemes: 73%|███████▎ | 1967/2703 [00:00<00:00, 3077.39it/s] word -> phonemes: 86%|████████▌ | 2325/2703 [00:00<00:00, 3232.89it/s] word -> phonemes: 98%|█████████▊| 2652/2703 [00:00<00:00, 2942.46it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3027.08it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 8%|▊ | 286/3515 [00:00<00:01, 2855.82it/s] word -> phonemes: 16%|█▋ | 572/3515 [00:00<00:01, 2471.45it/s] word -> phonemes: 25%|██▍ | 868/3515 [00:00<00:00, 2675.52it/s] word -> phonemes: 32%|███▏ | 1140/3515 [00:00<00:00, 2674.29it/s] word -> phonemes: 41%|████ | 1431/3515 [00:00<00:00, 2755.32it/s] word -> phonemes: 49%|████▊ | 1709/3515 [00:00<00:00, 2635.50it/s] word -> phonemes: 58%|█████▊ | 2033/3515 [00:00<00:00, 2821.89it/s] word -> phonemes: 66%|██████▌ | 2318/3515 [00:00<00:00, 2690.79it/s] word -> phonemes: 74%|███████▎ | 2590/3515 [00:00<00:00, 2681.64it/s] word -> phonemes: 82%|████████▏ | 2871/3515 [00:01<00:00, 2718.22it/s] word -> phonemes: 89%|████████▉ | 3145/3515 [00:01<00:00, 2528.15it/s] word -> phonemes: 98%|█████████▊| 3444/3515 [00:01<00:00, 2656.63it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2673.79it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 326/2703 [00:00<00:00, 3252.65it/s] word -> phonemes: 24%|██▍ | 652/2703 [00:00<00:00, 3192.36it/s] word -> phonemes: 37%|███▋ | 1011/2703 [00:00<00:00, 3369.84it/s] word -> phonemes: 51%|█████ | 1368/2703 [00:00<00:00, 3446.11it/s] word -> phonemes: 64%|██████▎ | 1718/2703 [00:00<00:00, 3465.18it/s] word -> phonemes: 76%|███████▋ | 2065/2703 [00:00<00:00, 3367.99it/s] word -> phonemes: 89%|████████▉ | 2403/2703 [00:00<00:00, 3174.44it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3207.26it/s] dev: 0%| | 0/2703 [00:00