/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_valid {'model_config': None, 'refresh': False} Loading model from Local mert_speech_test_valid 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: 12%|█▏ | 410/3515 [00:00<00:00, 4090.77it/s] word -> phonemes: 23%|██▎ | 820/3515 [00:00<00:00, 3798.85it/s] word -> phonemes: 37%|███▋ | 1287/3515 [00:00<00:00, 4178.41it/s] word -> phonemes: 49%|████▉ | 1735/3515 [00:00<00:00, 4292.25it/s] word -> phonemes: 62%|██████▏ | 2166/3515 [00:00<00:00, 3930.52it/s] word -> phonemes: 74%|███████▎ | 2588/3515 [00:00<00:00, 4020.05it/s] word -> phonemes: 86%|████████▌ | 3021/3515 [00:00<00:00, 4114.74it/s] word -> phonemes: 98%|█████████▊| 3436/3515 [00:00<00:00, 3913.83it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4012.98it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 460/2703 [00:00<00:00, 4356.60it/s] word -> phonemes: 34%|███▎ | 911/2703 [00:00<00:00, 4440.82it/s] word -> phonemes: 50%|█████ | 1356/2703 [00:00<00:00, 4189.35it/s] word -> phonemes: 66%|██████▌ | 1783/2703 [00:00<00:00, 4215.49it/s] word -> phonemes: 82%|████████▏ | 2218/2703 [00:00<00:00, 4260.86it/s] word -> phonemes: 98%|█████████▊| 2645/2703 [00:00<00:00, 2481.37it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3191.22it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 493/2703 [00:00<00:00, 4924.37it/s] word -> phonemes: 36%|███▋ | 986/2703 [00:00<00:00, 4762.34it/s] word -> phonemes: 56%|█████▌ | 1507/2703 [00:00<00:00, 4960.32it/s] word -> phonemes: 75%|███████▍ | 2022/2703 [00:00<00:00, 5031.07it/s] word -> phonemes: 93%|█████████▎| 2526/2703 [00:00<00:00, 4848.92it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4895.61it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 470/2703 [00:00<00:00, 4698.81it/s] word -> phonemes: 35%|███▍ | 940/2703 [00:00<00:00, 4586.67it/s] word -> phonemes: 54%|█████▍ | 1461/2703 [00:00<00:00, 4864.71it/s] word -> phonemes: 72%|███████▏ | 1950/2703 [00:00<00:00, 4870.73it/s] word -> phonemes: 90%|█████████ | 2438/2703 [00:00<00:00, 4795.01it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4743.66it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 10%|▉ | 350/3515 [00:00<00:00, 3493.48it/s] word -> phonemes: 22%|██▏ | 773/3515 [00:00<00:00, 3923.79it/s] word -> phonemes: 33%|███▎ | 1166/3515 [00:00<00:00, 3786.07it/s] word -> phonemes: 46%|████▌ | 1604/3515 [00:00<00:00, 4014.01it/s] word -> phonemes: 58%|█████▊ | 2054/3515 [00:00<00:00, 4185.34it/s] word -> phonemes: 71%|███████▏ | 2506/3515 [00:00<00:00, 4297.23it/s] word -> phonemes: 84%|████████▎ | 2937/3515 [00:00<00:00, 4218.95it/s] word -> phonemes: 96%|█████████▌| 3360/3515 [00:00<00:00, 4064.65it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4016.68it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 18%|█▊ | 474/2703 [00:00<00:00, 4733.15it/s] word -> phonemes: 37%|███▋ | 1011/2703 [00:00<00:00, 5106.87it/s] word -> phonemes: 56%|█████▋ | 1522/2703 [00:00<00:00, 4436.38it/s] word -> phonemes: 73%|███████▎ | 1975/2703 [00:00<00:00, 4320.82it/s] word -> phonemes: 92%|█████████▏| 2483/2703 [00:00<00:00, 4572.29it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4610.97it/s] dev: 0%| | 0/2703 [00:00