/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: 9%|▉ | 317/3515 [00:00<00:01, 3167.04it/s] word -> phonemes: 22%|██▏ | 772/3515 [00:00<00:00, 3977.91it/s] word -> phonemes: 33%|███▎ | 1170/3515 [00:00<00:00, 3930.01it/s] word -> phonemes: 45%|████▍ | 1569/3515 [00:00<00:00, 3951.82it/s] word -> phonemes: 56%|█████▌ | 1965/3515 [00:00<00:00, 3497.81it/s] word -> phonemes: 68%|██████▊ | 2376/3515 [00:00<00:00, 3688.19it/s] word -> phonemes: 79%|███████▉ | 2790/3515 [00:00<00:00, 3825.62it/s] word -> phonemes: 90%|█████████ | 3178/3515 [00:00<00:00, 3823.75it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3802.75it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 227/2703 [00:00<00:01, 2255.71it/s] word -> phonemes: 17%|█▋ | 453/2703 [00:00<00:01, 1929.27it/s] word -> phonemes: 27%|██▋ | 719/2703 [00:00<00:00, 2188.54it/s] word -> phonemes: 35%|███▍ | 942/2703 [00:00<00:00, 2136.46it/s] word -> phonemes: 45%|████▌ | 1228/2703 [00:00<00:00, 2379.70it/s] word -> phonemes: 55%|█████▌ | 1498/2703 [00:00<00:00, 2469.72it/s] word -> phonemes: 65%|██████▍ | 1748/2703 [00:00<00:00, 2367.17it/s] word -> phonemes: 74%|███████▍ | 2007/2703 [00:00<00:00, 2406.24it/s] word -> phonemes: 84%|████████▎ | 2263/2703 [00:00<00:00, 2451.16it/s] word -> phonemes: 93%|█████████▎| 2510/2703 [00:01<00:00, 2353.09it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2275.48it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|▉ | 269/2703 [00:00<00:00, 2688.97it/s] word -> phonemes: 24%|██▍ | 642/2703 [00:00<00:00, 3300.73it/s] word -> phonemes: 36%|███▌ | 973/2703 [00:00<00:00, 3041.31it/s] word -> phonemes: 47%|████▋ | 1280/2703 [00:00<00:00, 3005.37it/s] word -> phonemes: 62%|██████▏ | 1671/2703 [00:00<00:00, 3302.02it/s] word -> phonemes: 74%|███████▍ | 2004/2703 [00:00<00:00, 2447.23it/s] word -> phonemes: 84%|████████▍ | 2278/2703 [00:00<00:00, 2492.96it/s] word -> phonemes: 94%|█████████▍| 2548/2703 [00:00<00:00, 2513.54it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2677.51it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 9%|▉ | 250/2703 [00:00<00:00, 2498.15it/s] word -> phonemes: 18%|█▊ | 500/2703 [00:00<00:00, 2369.82it/s] word -> phonemes: 33%|███▎ | 885/2703 [00:00<00:00, 3017.25it/s] word -> phonemes: 44%|████▍ | 1189/2703 [00:00<00:00, 2565.79it/s] word -> phonemes: 54%|█████▍ | 1455/2703 [00:00<00:00, 2346.25it/s] word -> phonemes: 63%|██████▎ | 1697/2703 [00:00<00:00, 2076.65it/s] word -> phonemes: 71%|███████ | 1913/2703 [00:00<00:00, 1931.36it/s] word -> phonemes: 78%|███████▊ | 2112/2703 [00:00<00:00, 1924.30it/s] word -> phonemes: 94%|█████████▍| 2536/2703 [00:01<00:00, 2518.02it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2217.65it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 8%|▊ | 294/3515 [00:00<00:01, 2939.63it/s] word -> phonemes: 21%|██ | 722/3515 [00:00<00:00, 3716.99it/s] word -> phonemes: 31%|███ | 1094/3515 [00:00<00:00, 3593.36it/s] word -> phonemes: 44%|████▎ | 1534/3515 [00:00<00:00, 3902.69it/s] word -> phonemes: 55%|█████▌ | 1935/3515 [00:00<00:00, 3939.68it/s] word -> phonemes: 67%|██████▋ | 2349/3515 [00:00<00:00, 4005.64it/s] word -> phonemes: 78%|███████▊ | 2751/3515 [00:00<00:00, 3851.73it/s] word -> phonemes: 89%|████████▉ | 3138/3515 [00:00<00:00, 3707.67it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3779.49it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|█ | 272/2703 [00:00<00:00, 2678.59it/s] word -> phonemes: 20%|█▉ | 540/2703 [00:00<00:00, 2567.82it/s] word -> phonemes: 30%|██▉ | 798/2703 [00:00<00:00, 2391.10it/s] word -> phonemes: 39%|███▉ | 1052/2703 [00:00<00:00, 2442.32it/s] word -> phonemes: 48%|████▊ | 1298/2703 [00:00<00:00, 2221.64it/s] word -> phonemes: 58%|█████▊ | 1563/2703 [00:00<00:00, 2349.55it/s] word -> phonemes: 67%|██████▋ | 1802/2703 [00:00<00:00, 2267.88it/s] word -> phonemes: 77%|███████▋ | 2068/2703 [00:00<00:00, 2344.46it/s] word -> phonemes: 88%|████████▊ | 2376/2703 [00:00<00:00, 2531.03it/s] word -> phonemes: 97%|█████████▋| 2632/2703 [00:01<00:00, 2525.92it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2377.35it/s] dev: 0%| | 0/2703 [00:00