/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] - 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_speech_test_nocqt {'model_config': None, 'refresh': False} Loading model from Local mert_speech_test_nocqt 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: 9%|▉ | 308/3515 [00:00<00:01, 3074.93it/s] word -> phonemes: 22%|██▏ | 788/3515 [00:00<00:00, 4087.55it/s] word -> phonemes: 35%|███▍ | 1214/3515 [00:00<00:00, 4165.67it/s] word -> phonemes: 47%|████▋ | 1639/3515 [00:00<00:00, 4163.47it/s] word -> phonemes: 59%|█████▉ | 2079/3515 [00:00<00:00, 4245.32it/s] word -> phonemes: 72%|███████▏ | 2535/3515 [00:00<00:00, 4286.49it/s] word -> phonemes: 84%|████████▍ | 2964/3515 [00:00<00:00, 4264.85it/s] word -> phonemes: 96%|█████████▋| 3391/3515 [00:00<00:00, 4210.63it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4174.79it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 15%|█▌ | 409/2703 [00:00<00:00, 4089.82it/s] word -> phonemes: 30%|███ | 818/2703 [00:00<00:00, 3752.42it/s] word -> phonemes: 46%|████▌ | 1235/2703 [00:00<00:00, 3825.11it/s] word -> phonemes: 64%|██████▍ | 1742/2703 [00:00<00:00, 4242.59it/s] word -> phonemes: 84%|████████▍ | 2275/2703 [00:00<00:00, 4619.28it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4088.99it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 459/2703 [00:00<00:00, 4584.52it/s] word -> phonemes: 34%|███▍ | 918/2703 [00:00<00:00, 4173.32it/s] word -> phonemes: 50%|████▉ | 1338/2703 [00:00<00:00, 4099.40it/s] word -> phonemes: 65%|██████▍ | 1750/2703 [00:00<00:00, 3944.89it/s] word -> phonemes: 81%|████████▏ | 2198/2703 [00:00<00:00, 4127.36it/s] word -> phonemes: 97%|█████████▋| 2613/2703 [00:00<00:00, 4092.90it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4116.23it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 470/2703 [00:00<00:00, 4681.01it/s] word -> phonemes: 35%|███▍ | 939/2703 [00:00<00:00, 4277.13it/s] word -> phonemes: 51%|█████ | 1369/2703 [00:00<00:00, 3941.79it/s] word -> phonemes: 65%|██████▌ | 1766/2703 [00:00<00:00, 3866.31it/s] word -> phonemes: 83%|████████▎ | 2245/2703 [00:00<00:00, 4175.23it/s] word -> phonemes: 99%|█████████▊| 2666/2703 [00:00<00:00, 3861.85it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3984.20it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 423/3515 [00:00<00:00, 4220.40it/s] word -> phonemes: 24%|██▍ | 855/3515 [00:00<00:00, 4275.80it/s] word -> phonemes: 38%|███▊ | 1342/3515 [00:00<00:00, 4448.62it/s] word -> phonemes: 51%|█████ | 1787/3515 [00:00<00:00, 4438.70it/s] word -> phonemes: 63%|██████▎ | 2231/3515 [00:00<00:00, 4290.03it/s] word -> phonemes: 76%|███████▌ | 2661/3515 [00:00<00:00, 3989.61it/s] word -> phonemes: 87%|████████▋ | 3064/3515 [00:00<00:00, 3859.92it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4141.03it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 358/2703 [00:00<00:00, 3415.76it/s] word -> phonemes: 28%|██▊ | 765/2703 [00:00<00:00, 3752.16it/s] word -> phonemes: 42%|████▏ | 1142/2703 [00:00<00:00, 3758.47it/s] word -> phonemes: 58%|█████▊ | 1580/2703 [00:00<00:00, 3998.85it/s] word -> phonemes: 73%|███████▎ | 1981/2703 [00:00<00:00, 3777.87it/s] word -> phonemes: 89%|████████▉ | 2418/2703 [00:00<00:00, 3969.20it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3874.23it/s] dev: 0%| | 0/2703 [00:00