/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%|█ | 353/3515 [00:00<00:00, 3529.15it/s] word -> phonemes: 24%|██▎ | 827/3515 [00:00<00:00, 4240.96it/s] word -> phonemes: 38%|███▊ | 1320/3515 [00:00<00:00, 4555.37it/s] word -> phonemes: 51%|█████ | 1799/3515 [00:00<00:00, 4645.47it/s] word -> phonemes: 64%|██████▍ | 2264/3515 [00:00<00:00, 4306.72it/s] word -> phonemes: 77%|███████▋ | 2719/3515 [00:00<00:00, 4382.29it/s] word -> phonemes: 91%|█████████ | 3186/3515 [00:00<00:00, 4472.64it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4380.85it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 12%|█▏ | 321/2703 [00:00<00:00, 3127.56it/s] word -> phonemes: 25%|██▍ | 669/2703 [00:00<00:00, 3324.88it/s] word -> phonemes: 37%|███▋ | 1002/2703 [00:00<00:00, 3010.02it/s] word -> phonemes: 54%|█████▍ | 1472/2703 [00:00<00:00, 3630.75it/s] word -> phonemes: 68%|██████▊ | 1842/2703 [00:00<00:00, 3416.01it/s] word -> phonemes: 83%|████████▎ | 2241/2703 [00:00<00:00, 3567.61it/s] word -> phonemes: 98%|█████████▊| 2651/2703 [00:00<00:00, 3731.55it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3558.79it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 355/2703 [00:00<00:00, 3544.46it/s] word -> phonemes: 28%|██▊ | 754/2703 [00:00<00:00, 3805.63it/s] word -> phonemes: 42%|████▏ | 1135/2703 [00:00<00:00, 3570.28it/s] word -> phonemes: 61%|██████ | 1636/2703 [00:00<00:00, 4115.19it/s] word -> phonemes: 76%|███████▌ | 2051/2703 [00:00<00:00, 3989.93it/s] word -> phonemes: 92%|█████████▏| 2485/2703 [00:00<00:00, 4102.79it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4052.19it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 14%|█▍ | 372/2703 [00:00<00:00, 3716.81it/s] word -> phonemes: 29%|██▉ | 778/2703 [00:00<00:00, 3918.27it/s] word -> phonemes: 44%|████▍ | 1200/2703 [00:00<00:00, 4052.28it/s] word -> phonemes: 60%|█████▉ | 1616/2703 [00:00<00:00, 4093.71it/s] word -> phonemes: 75%|███████▍ | 2026/2703 [00:00<00:00, 4058.43it/s] word -> phonemes: 93%|█████████▎| 2513/2703 [00:00<00:00, 4329.93it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4226.62it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 10%|█ | 361/3515 [00:00<00:00, 3608.52it/s] word -> phonemes: 22%|██▏ | 766/3515 [00:00<00:00, 3817.35it/s] word -> phonemes: 33%|███▎ | 1148/3515 [00:00<00:00, 3735.23it/s] word -> phonemes: 43%|████▎ | 1522/3515 [00:00<00:00, 3670.81it/s] word -> phonemes: 55%|█████▍ | 1924/3515 [00:00<00:00, 3791.84it/s] word -> phonemes: 66%|██████▌ | 2304/3515 [00:00<00:00, 3785.73it/s] word -> phonemes: 76%|███████▋ | 2683/3515 [00:00<00:00, 3612.46it/s] word -> phonemes: 87%|████████▋ | 3058/3515 [00:00<00:00, 3641.50it/s] word -> phonemes: 98%|█████████▊| 3444/3515 [00:00<00:00, 3705.79it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3722.32it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 494/2703 [00:00<00:00, 4792.56it/s] word -> phonemes: 36%|███▌ | 974/2703 [00:00<00:00, 4054.73it/s] word -> phonemes: 54%|█████▍ | 1455/2703 [00:00<00:00, 4223.51it/s] word -> phonemes: 70%|██████▉ | 1882/2703 [00:00<00:00, 3840.09it/s] word -> phonemes: 84%|████████▍ | 2272/2703 [00:00<00:00, 3680.75it/s] word -> phonemes: 98%|█████████▊| 2649/2703 [00:00<00:00, 3707.66it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3874.13it/s] dev: 0%| | 0/2703 [00:00