/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 {'model_config': None, 'refresh': False} Loading model from Local mert_speech_test 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%|█ | 352/3515 [00:00<00:00, 3407.59it/s] word -> phonemes: 22%|██▏ | 783/3515 [00:00<00:00, 3930.52it/s] word -> phonemes: 35%|███▌ | 1237/3515 [00:00<00:00, 4205.96it/s] word -> phonemes: 47%|████▋ | 1659/3515 [00:00<00:00, 3909.11it/s] word -> phonemes: 60%|██████ | 2114/3515 [00:00<00:00, 4127.41it/s] word -> phonemes: 72%|███████▏ | 2530/3515 [00:00<00:00, 4015.45it/s] word -> phonemes: 84%|████████▎ | 2941/3515 [00:00<00:00, 4029.99it/s] word -> phonemes: 95%|█████████▌| 3346/3515 [00:00<00:00, 3884.94it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3962.41it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 16%|█▌ | 437/2703 [00:00<00:00, 4298.18it/s] word -> phonemes: 32%|███▏ | 871/2703 [00:00<00:00, 4320.62it/s] word -> phonemes: 48%|████▊ | 1304/2703 [00:00<00:00, 3889.11it/s] word -> phonemes: 68%|██████▊ | 1830/2703 [00:00<00:00, 4391.90it/s] word -> phonemes: 84%|████████▍ | 2276/2703 [00:00<00:00, 4297.47it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4162.47it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 14%|█▍ | 386/2703 [00:00<00:00, 3857.34it/s] word -> phonemes: 30%|███ | 815/2703 [00:00<00:00, 4103.82it/s] word -> phonemes: 45%|████▌ | 1226/2703 [00:00<00:00, 3976.60it/s] word -> phonemes: 63%|██████▎ | 1710/2703 [00:00<00:00, 4310.01it/s] word -> phonemes: 80%|███████▉ | 2157/2703 [00:00<00:00, 4366.60it/s] word -> phonemes: 96%|█████████▋| 2605/2703 [00:00<00:00, 4384.00it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4144.81it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 475/2703 [00:00<00:00, 4743.06it/s] word -> phonemes: 35%|███▌ | 950/2703 [00:00<00:00, 4410.30it/s] word -> phonemes: 54%|█████▍ | 1470/2703 [00:00<00:00, 4755.55it/s] word -> phonemes: 72%|███████▏ | 1948/2703 [00:00<00:00, 4653.89it/s] word -> phonemes: 91%|█████████▏| 2471/2703 [00:00<00:00, 4853.32it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4683.45it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 438/3515 [00:00<00:00, 4376.79it/s] word -> phonemes: 25%|██▌ | 893/3515 [00:00<00:00, 4476.55it/s] word -> phonemes: 38%|███▊ | 1341/3515 [00:00<00:00, 4446.03it/s] word -> phonemes: 51%|█████ | 1786/3515 [00:00<00:00, 4292.10it/s] word -> phonemes: 63%|██████▎ | 2216/3515 [00:00<00:00, 4194.43it/s] word -> phonemes: 75%|███████▌ | 2639/3515 [00:00<00:00, 4204.81it/s] word -> phonemes: 87%|████████▋ | 3060/3515 [00:00<00:00, 4161.07it/s] word -> phonemes: 99%|█████████▉| 3492/3515 [00:00<00:00, 4209.77it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4252.53it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 451/2703 [00:00<00:00, 4389.98it/s] word -> phonemes: 33%|███▎ | 890/2703 [00:00<00:00, 4154.10it/s] word -> phonemes: 48%|████▊ | 1307/2703 [00:00<00:00, 4124.67it/s] word -> phonemes: 65%|██████▌ | 1767/2703 [00:00<00:00, 4266.44it/s] word -> phonemes: 81%|████████ | 2195/2703 [00:00<00:00, 4193.26it/s] word -> phonemes: 97%|█████████▋| 2615/2703 [00:00<00:00, 3812.43it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4017.04it/s] dev: 0%| | 0/2703 [00:00