/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") /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 {'model_config': None, 'refresh': False} Loading model from Local mert_test_8x_400k 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: 10%|█ | 367/3515 [00:00<00:00, 3663.19it/s] word -> phonemes: 21%|██ | 734/3515 [00:00<00:00, 3449.19it/s] word -> phonemes: 32%|███▏ | 1141/3515 [00:00<00:00, 3722.60it/s] word -> phonemes: 44%|████▍ | 1547/3515 [00:00<00:00, 3850.74it/s] word -> phonemes: 55%|█████▌ | 1934/3515 [00:00<00:00, 3731.91it/s] word -> phonemes: 66%|██████▋ | 2335/3515 [00:00<00:00, 3821.94it/s] word -> phonemes: 78%|███████▊ | 2759/3515 [00:00<00:00, 3954.19it/s] word -> phonemes: 90%|████████▉ | 3156/3515 [00:00<00:00, 3948.73it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3869.54it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 303/2703 [00:00<00:00, 3027.71it/s] word -> phonemes: 24%|██▎ | 641/2703 [00:00<00:00, 3232.37it/s] word -> phonemes: 37%|███▋ | 1007/2703 [00:00<00:00, 3426.64it/s] word -> phonemes: 50%|████▉ | 1350/2703 [00:00<00:00, 3097.75it/s] word -> phonemes: 62%|██████▏ | 1664/2703 [00:00<00:00, 2874.07it/s] word -> phonemes: 72%|███████▏ | 1956/2703 [00:00<00:00, 2830.72it/s] word -> phonemes: 86%|████████▌ | 2331/2703 [00:00<00:00, 3107.31it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3254.40it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 16%|█▋ | 444/2703 [00:00<00:00, 4438.95it/s] word -> phonemes: 34%|███▎ | 908/2703 [00:00<00:00, 4555.22it/s] word -> phonemes: 53%|█████▎ | 1421/2703 [00:00<00:00, 4733.40it/s] word -> phonemes: 71%|███████ | 1917/2703 [00:00<00:00, 4821.16it/s] word -> phonemes: 89%|████████▉ | 2399/2703 [00:00<00:00, 4734.53it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4627.59it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 451/2703 [00:00<00:00, 4503.34it/s] word -> phonemes: 33%|███▎ | 902/2703 [00:00<00:00, 3853.84it/s] word -> phonemes: 48%|████▊ | 1294/2703 [00:00<00:00, 2877.71it/s] word -> phonemes: 59%|█████▉ | 1605/2703 [00:00<00:00, 2722.64it/s] word -> phonemes: 72%|███████▏ | 1957/2703 [00:00<00:00, 2951.03it/s] word -> phonemes: 84%|████████▍ | 2266/2703 [00:00<00:00, 2757.87it/s] word -> phonemes: 97%|█████████▋| 2624/2703 [00:00<00:00, 2955.43it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2976.76it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█▏ | 404/3515 [00:00<00:00, 4031.03it/s] word -> phonemes: 23%|██▎ | 808/3515 [00:00<00:00, 3813.74it/s] word -> phonemes: 37%|███▋ | 1288/3515 [00:00<00:00, 4247.26it/s] word -> phonemes: 49%|████▉ | 1718/3515 [00:00<00:00, 4232.48it/s] word -> phonemes: 62%|██████▏ | 2187/3515 [00:00<00:00, 4392.45it/s] word -> phonemes: 75%|███████▍ | 2628/3515 [00:00<00:00, 3795.90it/s] word -> phonemes: 86%|████████▋ | 3035/3515 [00:00<00:00, 3875.51it/s] word -> phonemes: 98%|█████████▊| 3448/3515 [00:00<00:00, 3949.33it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3974.15it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 9%|▉ | 252/2703 [00:00<00:00, 2510.30it/s] word -> phonemes: 19%|█▊ | 504/2703 [00:00<00:00, 2510.90it/s] word -> phonemes: 28%|██▊ | 756/2703 [00:00<00:00, 2470.45it/s] word -> phonemes: 39%|███▉ | 1062/2703 [00:00<00:00, 2570.73it/s] word -> phonemes: 50%|████▉ | 1351/2703 [00:00<00:00, 2680.10it/s] word -> phonemes: 64%|██████▍ | 1732/2703 [00:00<00:00, 3034.98it/s] word -> phonemes: 75%|███████▌ | 2037/2703 [00:00<00:00, 2670.59it/s] word -> phonemes: 91%|█████████ | 2449/2703 [00:00<00:00, 3085.06it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2730.21it/s] dev: 0%| | 0/2703 [00:00