/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') Some weights of the model checkpoint at m-a-p/MERT-v1-95M were not used when initializing MERTModel: ['encoder.pos_conv_embed.conv.weight_v', 'encoder.pos_conv_embed.conv.weight_g'] - This IS expected if you are initializing MERTModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing MERTModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). Some weights of MERTModel were not initialized from the model checkpoint at m-a-p/MERT-v1-95M and are newly initialized: ['encoder.pos_conv_embed.conv.parametrizations.weight.original1', 'encoder.pos_conv_embed.conv.parametrizations.weight.original0'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. [Featurizer] - The selected feature hidden_states's downsample rate is 320 [Runner] - Start a new experiment m-a-p/MERT-v1-95M {'model_config': None, 'refresh': False} overall: 0%| | 0/4000 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 428/3515 [00:00<00:00, 4275.10it/s] word -> phonemes: 24%|██▍ | 856/3515 [00:00<00:00, 4088.63it/s] word -> phonemes: 36%|███▋ | 1276/3515 [00:00<00:00, 4137.84it/s] word -> phonemes: 51%|█████ | 1780/3515 [00:00<00:00, 4485.75it/s] word -> phonemes: 65%|██████▍ | 2279/3515 [00:00<00:00, 4665.24it/s] word -> phonemes: 78%|███████▊ | 2747/3515 [00:00<00:00, 4360.28it/s] word -> phonemes: 91%|█████████ | 3187/3515 [00:00<00:00, 4054.89it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4256.76it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 7%|▋ | 183/2703 [00:00<00:01, 1707.29it/s] word -> phonemes: 19%|█▉ | 516/2703 [00:00<00:00, 2631.90it/s] word -> phonemes: 29%|██▉ | 782/2703 [00:00<00:00, 2620.52it/s] word -> phonemes: 39%|███▉ | 1048/2703 [00:00<00:00, 2622.18it/s] word -> phonemes: 49%|████▊ | 1312/2703 [00:00<00:00, 2162.47it/s] word -> phonemes: 58%|█████▊ | 1563/2703 [00:00<00:00, 2257.37it/s] word -> phonemes: 67%|██████▋ | 1799/2703 [00:00<00:00, 2287.07it/s] word -> phonemes: 77%|███████▋ | 2080/2703 [00:00<00:00, 2441.37it/s] word -> phonemes: 87%|████████▋ | 2361/2703 [00:00<00:00, 2529.82it/s] word -> phonemes: 97%|█████████▋| 2618/2703 [00:01<00:00, 2232.88it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2143.72it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 304/2703 [00:00<00:00, 3035.65it/s] word -> phonemes: 22%|██▏ | 608/2703 [00:00<00:01, 1996.48it/s] word -> phonemes: 31%|███ | 828/2703 [00:00<00:00, 1957.45it/s] word -> phonemes: 42%|████▏ | 1124/2703 [00:00<00:00, 2227.13it/s] word -> phonemes: 54%|█████▎ | 1449/2703 [00:00<00:00, 2545.44it/s] word -> phonemes: 70%|██████▉ | 1890/2703 [00:00<00:00, 3112.92it/s] word -> phonemes: 82%|████████▏ | 2215/2703 [00:00<00:00, 2889.71it/s] word -> phonemes: 93%|█████████▎| 2516/2703 [00:00<00:00, 2781.13it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2500.85it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 8%|▊ | 217/2703 [00:00<00:01, 2140.50it/s] word -> phonemes: 16%|█▌ | 432/2703 [00:00<00:01, 1695.05it/s] word -> phonemes: 23%|██▎ | 609/2703 [00:00<00:01, 1723.73it/s] word -> phonemes: 30%|███ | 823/2703 [00:00<00:01, 1874.23it/s] word -> phonemes: 40%|████ | 1090/2703 [00:00<00:00, 2144.62it/s] word -> phonemes: 51%|█████ | 1372/2703 [00:00<00:00, 2363.58it/s] word -> phonemes: 60%|█████▉ | 1612/2703 [00:00<00:00, 2211.77it/s] word -> phonemes: 68%|██████▊ | 1845/2703 [00:00<00:00, 2246.59it/s] word -> phonemes: 80%|███████▉ | 2159/2703 [00:00<00:00, 2495.85it/s] word -> phonemes: 89%|████████▉ | 2412/2703 [00:01<00:00, 2214.17it/s] word -> phonemes: 98%|█████████▊| 2641/2703 [00:01<00:00, 1838.58it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2032.65it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 11%|█ | 372/3515 [00:00<00:00, 3717.58it/s] word -> phonemes: 24%|██▎ | 831/3515 [00:00<00:00, 4229.20it/s] word -> phonemes: 37%|███▋ | 1318/3515 [00:00<00:00, 4518.04it/s] word -> phonemes: 50%|█████ | 1770/3515 [00:00<00:00, 4403.50it/s] word -> phonemes: 63%|██████▎ | 2211/3515 [00:00<00:00, 4221.15it/s] word -> phonemes: 76%|███████▌ | 2658/3515 [00:00<00:00, 4300.88it/s] word -> phonemes: 88%|████████▊ | 3106/3515 [00:00<00:00, 4355.89it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4308.38it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 297/2703 [00:00<00:00, 2648.14it/s] word -> phonemes: 21%|██ | 562/2703 [00:00<00:01, 1823.26it/s] word -> phonemes: 28%|██▊ | 758/2703 [00:00<00:01, 1769.28it/s] word -> phonemes: 35%|███▌ | 955/2703 [00:00<00:00, 1815.67it/s] word -> phonemes: 48%|████▊ | 1306/2703 [00:00<00:00, 2312.58it/s] word -> phonemes: 57%|█████▋ | 1546/2703 [00:00<00:00, 2150.63it/s] word -> phonemes: 65%|██████▌ | 1770/2703 [00:00<00:00, 2175.76it/s] word -> phonemes: 74%|███████▍ | 2006/2703 [00:00<00:00, 2224.17it/s] word -> phonemes: 83%|████████▎ | 2233/2703 [00:01<00:00, 1885.32it/s] word -> phonemes: 90%|████████▉ | 2432/2703 [00:01<00:00, 1757.72it/s] word -> phonemes: 97%|█████████▋| 2616/2703 [00:01<00:00, 1709.36it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 1845.60it/s] dev: 0%| | 0/2703 [00:00