/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") 2023-09-28 16:05:30 | 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_test_demuc_vocal {'model_config': None, 'refresh': False} Loading model from Local mert_test_demuc_vocal 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%|▌ | 216/3515 [00:00<00:01, 2159.42it/s] word -> phonemes: 13%|█▎ | 464/3515 [00:00<00:01, 2346.40it/s] word -> phonemes: 21%|██▏ | 748/3515 [00:00<00:01, 2569.57it/s] word -> phonemes: 29%|██▉ | 1027/3515 [00:00<00:00, 2656.20it/s] word -> phonemes: 37%|███▋ | 1293/3515 [00:00<00:00, 2636.38it/s] word -> phonemes: 44%|████▍ | 1557/3515 [00:00<00:00, 2589.96it/s] word -> phonemes: 52%|█████▏ | 1817/3515 [00:00<00:00, 2325.56it/s] word -> phonemes: 60%|█████▉ | 2096/3515 [00:00<00:00, 2459.10it/s] word -> phonemes: 67%|██████▋ | 2366/3515 [00:00<00:00, 2527.30it/s] word -> phonemes: 75%|███████▍ | 2623/3515 [00:01<00:00, 2503.36it/s] word -> phonemes: 82%|████████▏ | 2897/3515 [00:01<00:00, 2571.45it/s] word -> phonemes: 90%|█████████ | 3169/3515 [00:01<00:00, 2614.94it/s] word -> phonemes: 98%|█████████▊| 3432/3515 [00:01<00:00, 2463.54it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2507.81it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 315/2703 [00:00<00:00, 3146.36it/s] word -> phonemes: 23%|██▎ | 630/2703 [00:00<00:00, 3104.23it/s] word -> phonemes: 35%|███▍ | 941/2703 [00:00<00:00, 2981.79it/s] word -> phonemes: 46%|████▌ | 1240/2703 [00:00<00:00, 2807.61it/s] word -> phonemes: 56%|█████▋ | 1523/2703 [00:00<00:00, 2552.72it/s] word -> phonemes: 66%|██████▌ | 1782/2703 [00:00<00:00, 2423.47it/s] word -> phonemes: 75%|███████▍ | 2027/2703 [00:00<00:00, 2335.72it/s] word -> phonemes: 84%|████████▎ | 2263/2703 [00:00<00:00, 2316.11it/s] word -> phonemes: 92%|█████████▏| 2496/2703 [00:01<00:00, 2104.23it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2411.50it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 222/2703 [00:00<00:01, 2218.02it/s] word -> phonemes: 17%|█▋ | 450/2703 [00:00<00:01, 2249.48it/s] word -> phonemes: 25%|██▍ | 675/2703 [00:00<00:00, 2197.28it/s] word -> phonemes: 36%|███▌ | 968/2703 [00:00<00:00, 2482.13it/s] word -> phonemes: 47%|████▋ | 1270/2703 [00:00<00:00, 2673.44it/s] word -> phonemes: 59%|█████▊ | 1587/2703 [00:00<00:00, 2840.91it/s] word -> phonemes: 71%|███████ | 1906/2703 [00:00<00:00, 2954.34it/s] word -> phonemes: 82%|████████▏ | 2219/2703 [00:00<00:00, 3007.65it/s] word -> phonemes: 93%|█████████▎| 2521/2703 [00:00<00:00, 2809.91it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2670.16it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 7%|▋ | 196/2703 [00:00<00:01, 1958.29it/s] word -> phonemes: 17%|█▋ | 469/2703 [00:00<00:00, 2409.76it/s] word -> phonemes: 28%|██▊ | 763/2703 [00:00<00:00, 2649.61it/s] word -> phonemes: 39%|███▉ | 1062/2703 [00:00<00:00, 2780.45it/s] word -> phonemes: 50%|████▉ | 1341/2703 [00:00<00:00, 2680.15it/s] word -> phonemes: 61%|██████ | 1643/2703 [00:00<00:00, 2789.76it/s] word -> phonemes: 72%|███████▏ | 1946/2703 [00:00<00:00, 2866.12it/s] word -> phonemes: 83%|████████▎ | 2240/2703 [00:00<00:00, 2889.11it/s] word -> phonemes: 94%|█████████▎| 2530/2703 [00:00<00:00, 2890.30it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2779.41it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 7%|▋ | 261/3515 [00:00<00:01, 2609.60it/s] word -> phonemes: 15%|█▍ | 522/3515 [00:00<00:01, 2598.43it/s] word -> phonemes: 23%|██▎ | 795/3515 [00:00<00:01, 2653.78it/s] word -> phonemes: 30%|███ | 1061/3515 [00:00<00:00, 2603.66it/s] word -> phonemes: 38%|███▊ | 1322/3515 [00:00<00:00, 2337.34it/s] word -> phonemes: 44%|████▍ | 1560/3515 [00:00<00:00, 2107.92it/s] word -> phonemes: 51%|█████ | 1777/3515 [00:00<00:00, 1962.55it/s] word -> phonemes: 56%|█████▋ | 1978/3515 [00:00<00:00, 1879.19it/s] word -> phonemes: 64%|██████▍ | 2248/3515 [00:01<00:00, 2099.79it/s] word -> phonemes: 70%|███████ | 2464/3515 [00:01<00:00, 2029.92it/s] word -> phonemes: 76%|███████▌ | 2671/3515 [00:01<00:00, 2013.32it/s] word -> phonemes: 83%|████████▎ | 2933/3515 [00:01<00:00, 2183.34it/s] word -> phonemes: 91%|█████████ | 3190/3515 [00:01<00:00, 2292.29it/s] word -> phonemes: 98%|█████████▊| 3446/3515 [00:01<00:00, 2367.66it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2238.45it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 6%|▌ | 167/2703 [00:00<00:01, 1662.79it/s] word -> phonemes: 14%|█▎ | 369/2703 [00:00<00:01, 1871.60it/s] word -> phonemes: 21%|██ | 570/2703 [00:00<00:01, 1930.79it/s] word -> phonemes: 29%|██▉ | 786/2703 [00:00<00:00, 2019.64it/s] word -> phonemes: 37%|███▋ | 1003/2703 [00:00<00:00, 2071.65it/s] word -> phonemes: 45%|████▍ | 1213/2703 [00:00<00:00, 2080.15it/s] word -> phonemes: 53%|█████▎ | 1422/2703 [00:00<00:00, 2075.27it/s] word -> phonemes: 63%|██████▎ | 1701/2703 [00:00<00:00, 2300.21it/s] word -> phonemes: 74%|███████▍ | 2009/2703 [00:00<00:00, 2540.99it/s] word -> phonemes: 86%|████████▌ | 2321/2703 [00:01<00:00, 2716.76it/s] word -> phonemes: 97%|█████████▋| 2625/2703 [00:01<00:00, 2814.14it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2391.01it/s] dev: 0%| | 0/2703 [00:00