/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 02:45:03 | 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_norm2 {'model_config': None, 'refresh': False} using suno's k-means clusters: mert_test_8x_400k_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: 8%|▊ | 286/3515 [00:00<00:01, 2850.42it/s] word -> phonemes: 16%|█▋ | 572/3515 [00:00<00:01, 2852.81it/s] word -> phonemes: 25%|██▍ | 868/3515 [00:00<00:00, 2898.84it/s] word -> phonemes: 33%|███▎ | 1169/3515 [00:00<00:00, 2939.11it/s] word -> phonemes: 42%|████▏ | 1469/3515 [00:00<00:00, 2957.45it/s] word -> phonemes: 50%|█████ | 1765/3515 [00:00<00:00, 2936.24it/s] word -> phonemes: 59%|█████▊ | 2059/3515 [00:00<00:00, 2815.85it/s] word -> phonemes: 67%|██████▋ | 2342/3515 [00:00<00:00, 2736.63it/s] word -> phonemes: 74%|███████▍ | 2617/3515 [00:00<00:00, 2661.70it/s] word -> phonemes: 82%|████████▏ | 2884/3515 [00:01<00:00, 2461.60it/s] word -> phonemes: 89%|████████▉ | 3133/3515 [00:01<00:00, 2179.27it/s] word -> phonemes: 96%|█████████▌| 3358/3515 [00:01<00:00, 2071.69it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2456.69it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 335/2703 [00:00<00:00, 3348.77it/s] word -> phonemes: 25%|██▍ | 670/2703 [00:00<00:00, 3303.09it/s] word -> phonemes: 37%|███▋ | 1001/2703 [00:00<00:00, 2806.31it/s] word -> phonemes: 48%|████▊ | 1289/2703 [00:00<00:00, 2705.55it/s] word -> phonemes: 60%|██████ | 1623/2703 [00:00<00:00, 2910.71it/s] word -> phonemes: 72%|███████▏ | 1955/2703 [00:00<00:00, 1845.88it/s] word -> phonemes: 81%|████████ | 2188/2703 [00:00<00:00, 1949.82it/s] word -> phonemes: 90%|████████▉ | 2421/2703 [00:01<00:00, 1908.72it/s] word -> phonemes: 98%|█████████▊| 2637/2703 [00:01<00:00, 1955.11it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2203.53it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 303/2703 [00:00<00:00, 3023.82it/s] word -> phonemes: 23%|██▎ | 625/2703 [00:00<00:00, 3135.80it/s] word -> phonemes: 35%|███▍ | 939/2703 [00:00<00:01, 1536.40it/s] word -> phonemes: 45%|████▍ | 1208/2703 [00:00<00:00, 1815.32it/s] word -> phonemes: 57%|█████▋ | 1531/2703 [00:00<00:00, 2177.60it/s] word -> phonemes: 67%|██████▋ | 1807/2703 [00:00<00:00, 2333.25it/s] word -> phonemes: 78%|███████▊ | 2104/2703 [00:00<00:00, 2508.12it/s] word -> phonemes: 89%|████████▊ | 2395/2703 [00:01<00:00, 2620.33it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2393.16it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 277/2703 [00:00<00:00, 2766.42it/s] word -> phonemes: 22%|██▏ | 587/2703 [00:00<00:00, 2960.44it/s] word -> phonemes: 34%|███▎ | 908/2703 [00:00<00:00, 3069.78it/s] word -> phonemes: 45%|████▍ | 1215/2703 [00:00<00:00, 3068.33it/s] word -> phonemes: 57%|█████▋ | 1528/2703 [00:00<00:00, 3088.36it/s] word -> phonemes: 68%|██████▊ | 1843/2703 [00:00<00:00, 3108.23it/s] word -> phonemes: 80%|███████▉ | 2154/2703 [00:00<00:00, 2943.12it/s] word -> phonemes: 91%|█████████ | 2462/2703 [00:00<00:00, 2984.72it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3006.17it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 6%|▌ | 216/3515 [00:00<00:01, 2159.65it/s] word -> phonemes: 13%|█▎ | 452/3515 [00:00<00:01, 2275.74it/s] word -> phonemes: 21%|██ | 737/3515 [00:00<00:01, 2534.78it/s] word -> phonemes: 29%|██▉ | 1014/3515 [00:00<00:00, 2627.08it/s] word -> phonemes: 37%|███▋ | 1302/3515 [00:00<00:00, 2716.63it/s] word -> phonemes: 45%|████▍ | 1574/3515 [00:00<00:00, 2591.49it/s] word -> phonemes: 52%|█████▏ | 1835/3515 [00:00<00:00, 2568.61it/s] word -> phonemes: 60%|██████ | 2119/3515 [00:00<00:00, 2652.16it/s] word -> phonemes: 68%|██████▊ | 2386/3515 [00:00<00:00, 2654.92it/s] word -> phonemes: 76%|███████▌ | 2666/3515 [00:01<00:00, 2697.76it/s] word -> phonemes: 84%|████████▎ | 2942/3515 [00:01<00:00, 2716.52it/s] word -> phonemes: 91%|█████████▏| 3214/3515 [00:01<00:00, 2519.01it/s] word -> phonemes: 99%|█████████▉| 3480/3515 [00:01<00:00, 2558.84it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 2587.72it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 320/2703 [00:00<00:00, 3198.62it/s] word -> phonemes: 24%|██▎ | 640/2703 [00:00<00:00, 3012.09it/s] word -> phonemes: 36%|███▌ | 962/2703 [00:00<00:00, 3103.58it/s] word -> phonemes: 47%|████▋ | 1282/2703 [00:00<00:00, 3139.14it/s] word -> phonemes: 59%|█████▉ | 1597/2703 [00:00<00:00, 2938.01it/s] word -> phonemes: 70%|███████ | 1894/2703 [00:00<00:00, 2638.44it/s] word -> phonemes: 80%|████████ | 2164/2703 [00:00<00:00, 2442.50it/s] word -> phonemes: 89%|████████▉ | 2414/2703 [00:00<00:00, 2290.61it/s] word -> phonemes: 98%|█████████▊| 2647/2703 [00:01<00:00, 2208.67it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2527.69it/s] dev: 0%| | 0/2703 [00:00