/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_g', 'encoder.pos_conv_embed.conv.weight_v'] - 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%|█▏ | 421/3515 [00:00<00:00, 4208.87it/s] word -> phonemes: 26%|██▌ | 898/3515 [00:00<00:00, 4535.13it/s] word -> phonemes: 39%|███▉ | 1388/3515 [00:00<00:00, 4698.03it/s] word -> phonemes: 53%|█████▎ | 1858/3515 [00:00<00:00, 4302.81it/s] word -> phonemes: 65%|██████▌ | 2293/3515 [00:00<00:00, 4198.82it/s] word -> phonemes: 78%|███████▊ | 2752/3515 [00:00<00:00, 4322.46it/s] word -> phonemes: 91%|█████████▏| 3215/3515 [00:00<00:00, 4417.98it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4394.66it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 6%|▌ | 161/2703 [00:00<00:01, 1608.96it/s] word -> phonemes: 19%|█▊ | 505/2703 [00:00<00:00, 2683.49it/s] word -> phonemes: 36%|███▋ | 983/2703 [00:00<00:00, 3570.98it/s] word -> phonemes: 54%|█████▍ | 1457/2703 [00:00<00:00, 4025.03it/s] word -> phonemes: 69%|██████▉ | 1859/2703 [00:00<00:00, 2491.45it/s] word -> phonemes: 82%|████████▏ | 2205/2703 [00:00<00:00, 2723.74it/s] word -> phonemes: 94%|█████████▍| 2543/2703 [00:00<00:00, 2881.41it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2765.48it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 5%|▍ | 124/2703 [00:00<00:02, 1172.94it/s] word -> phonemes: 15%|█▍ | 401/2703 [00:00<00:01, 2088.69it/s] word -> phonemes: 28%|██▊ | 745/2703 [00:00<00:00, 2696.66it/s] word -> phonemes: 38%|███▊ | 1017/2703 [00:00<00:00, 2386.72it/s] word -> phonemes: 47%|████▋ | 1262/2703 [00:00<00:00, 2263.08it/s] word -> phonemes: 55%|█████▌ | 1493/2703 [00:00<00:00, 1838.31it/s] word -> phonemes: 76%|███████▋ | 2063/2703 [00:00<00:00, 2848.08it/s] word -> phonemes: 91%|█████████ | 2466/2703 [00:00<00:00, 3153.20it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2515.21it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 4%|▍ | 107/2703 [00:00<00:02, 1030.10it/s] word -> phonemes: 16%|█▌ | 429/2703 [00:00<00:00, 2289.60it/s] word -> phonemes: 27%|██▋ | 738/2703 [00:00<00:00, 2650.67it/s] word -> phonemes: 37%|███▋ | 1005/2703 [00:00<00:00, 2402.38it/s] word -> phonemes: 46%|████▌ | 1250/2703 [00:00<00:00, 1828.26it/s] word -> phonemes: 59%|█████▉ | 1599/2703 [00:00<00:00, 2270.42it/s] word -> phonemes: 75%|███████▍ | 2018/2703 [00:00<00:00, 2799.17it/s] word -> phonemes: 91%|█████████▏| 2471/2703 [00:00<00:00, 3287.68it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2700.82it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 432/3515 [00:00<00:00, 4314.16it/s] word -> phonemes: 25%|██▍ | 864/3515 [00:00<00:00, 4075.42it/s] word -> phonemes: 36%|███▌ | 1273/3515 [00:00<00:00, 4066.44it/s] word -> phonemes: 49%|████▉ | 1737/3515 [00:00<00:00, 4284.81it/s] word -> phonemes: 63%|██████▎ | 2213/3515 [00:00<00:00, 4450.88it/s] word -> phonemes: 76%|███████▌ | 2659/3515 [00:00<00:00, 4403.65it/s] word -> phonemes: 88%|████████▊ | 3100/3515 [00:00<00:00, 4316.17it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4239.95it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 9%|▊ | 230/2703 [00:00<00:01, 2222.77it/s] word -> phonemes: 17%|█▋ | 453/2703 [00:00<00:01, 2144.63it/s] word -> phonemes: 25%|██▍ | 668/2703 [00:00<00:01, 1985.32it/s] word -> phonemes: 38%|███▊ | 1035/2703 [00:00<00:00, 2606.72it/s] word -> phonemes: 48%|████▊ | 1301/2703 [00:00<00:00, 1907.28it/s] word -> phonemes: 65%|██████▌ | 1765/2703 [00:00<00:00, 2627.98it/s] word -> phonemes: 76%|███████▋ | 2065/2703 [00:00<00:00, 2723.31it/s] word -> phonemes: 87%|████████▋ | 2365/2703 [00:00<00:00, 2678.04it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:01<00:00, 2603.51it/s] dev: 0%| | 0/2703 [00:00