/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%|█ | 368/3515 [00:00<00:00, 3670.26it/s] word -> phonemes: 21%|██ | 736/3515 [00:00<00:00, 3444.72it/s] word -> phonemes: 33%|███▎ | 1145/3515 [00:00<00:00, 3726.06it/s] word -> phonemes: 44%|████▍ | 1551/3515 [00:00<00:00, 3853.65it/s] word -> phonemes: 55%|█████▌ | 1938/3515 [00:00<00:00, 3726.25it/s] word -> phonemes: 67%|██████▋ | 2340/3515 [00:00<00:00, 3821.95it/s] word -> phonemes: 79%|███████▊ | 2764/3515 [00:00<00:00, 3946.58it/s] word -> phonemes: 90%|████████▉ | 3161/3515 [00:00<00:00, 3953.10it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3868.61it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 462/2703 [00:00<00:00, 4616.22it/s] word -> phonemes: 39%|███▉ | 1057/2703 [00:00<00:00, 5400.25it/s] word -> phonemes: 59%|█████▉ | 1598/2703 [00:00<00:00, 4993.32it/s] word -> phonemes: 80%|████████ | 2164/2703 [00:00<00:00, 5121.70it/s] word -> phonemes: 99%|█████████▉| 2679/2703 [00:00<00:00, 4978.92it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 5019.98it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 14%|█▍ | 389/2703 [00:00<00:00, 3879.47it/s] word -> phonemes: 30%|███ | 816/2703 [00:00<00:00, 4107.08it/s] word -> phonemes: 48%|████▊ | 1310/2703 [00:00<00:00, 4484.40it/s] word -> phonemes: 67%|██████▋ | 1810/2703 [00:00<00:00, 4675.18it/s] word -> phonemes: 84%|████████▍ | 2278/2703 [00:00<00:00, 4433.45it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4545.55it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▌ | 406/2703 [00:00<00:00, 4059.26it/s] word -> phonemes: 32%|███▏ | 866/2703 [00:00<00:00, 4346.27it/s] word -> phonemes: 48%|████▊ | 1301/2703 [00:00<00:00, 3949.62it/s] word -> phonemes: 66%|██████▋ | 1795/2703 [00:00<00:00, 4313.13it/s] word -> phonemes: 83%|████████▎ | 2231/2703 [00:00<00:00, 4146.45it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4320.99it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█ | 372/3515 [00:00<00:00, 3615.56it/s] word -> phonemes: 23%|██▎ | 814/3515 [00:00<00:00, 4081.95it/s] word -> phonemes: 35%|███▍ | 1223/3515 [00:00<00:00, 4062.65it/s] word -> phonemes: 47%|████▋ | 1641/3515 [00:00<00:00, 4108.10it/s] word -> phonemes: 59%|█████▉ | 2071/3515 [00:00<00:00, 4175.57it/s] word -> phonemes: 72%|███████▏ | 2521/3515 [00:00<00:00, 4283.85it/s] word -> phonemes: 84%|████████▍ | 2950/3515 [00:00<00:00, 4185.87it/s] word -> phonemes: 96%|█████████▌| 3370/3515 [00:00<00:00, 4030.72it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4025.69it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 14%|█▎ | 369/2703 [00:00<00:00, 3570.78it/s] word -> phonemes: 27%|██▋ | 727/2703 [00:00<00:00, 3476.64it/s] word -> phonemes: 42%|████▏ | 1145/2703 [00:00<00:00, 3675.74it/s] word -> phonemes: 60%|██████ | 1629/2703 [00:00<00:00, 4119.47it/s] word -> phonemes: 76%|███████▌ | 2043/2703 [00:00<00:00, 3902.42it/s] word -> phonemes: 91%|█████████ | 2461/2703 [00:00<00:00, 3991.25it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3855.68it/s] dev: 0%| | 0/2703 [00:00