/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.original0', 'encoder.pos_conv_embed.conv.parametrizations.weight.original1'] 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: 7%|▋ | 261/3515 [00:00<00:01, 2609.21it/s] word -> phonemes: 15%|█▍ | 522/3515 [00:00<00:01, 2460.85it/s] word -> phonemes: 22%|██▏ | 782/3515 [00:00<00:01, 2519.74it/s] word -> phonemes: 30%|██▉ | 1043/3515 [00:00<00:00, 2552.76it/s] word -> phonemes: 41%|████ | 1436/3515 [00:00<00:00, 3041.81it/s] word -> phonemes: 51%|█████ | 1788/3515 [00:00<00:00, 3184.91it/s] word -> phonemes: 63%|██████▎ | 2203/3515 [00:00<00:00, 3495.90it/s] word -> phonemes: 73%|███████▎ | 2554/3515 [00:00<00:00, 3253.46it/s] word -> phonemes: 82%|████████▏ | 2883/3515 [00:00<00:00, 3178.42it/s] word -> phonemes: 91%|█████████ | 3204/3515 [00:01<00:00, 3162.39it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:01<00:00, 3064.75it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█ | 294/2703 [00:00<00:00, 2769.16it/s] word -> phonemes: 23%|██▎ | 631/2703 [00:00<00:00, 3111.49it/s] word -> phonemes: 35%|███▍ | 943/2703 [00:00<00:00, 2995.11it/s] word -> phonemes: 46%|████▌ | 1244/2703 [00:00<00:00, 2890.36it/s] word -> phonemes: 58%|█████▊ | 1557/2703 [00:00<00:00, 2972.51it/s] word -> phonemes: 73%|███████▎ | 1979/2703 [00:00<00:00, 3381.76it/s] word -> phonemes: 87%|████████▋ | 2364/2703 [00:00<00:00, 3502.12it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3226.49it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 9%|▉ | 241/2703 [00:00<00:01, 2407.83it/s] word -> phonemes: 19%|█▉ | 517/2703 [00:00<00:00, 2613.32it/s] word -> phonemes: 29%|██▉ | 779/2703 [00:00<00:00, 2431.50it/s] word -> phonemes: 43%|████▎ | 1150/2703 [00:00<00:00, 2912.12it/s] word -> phonemes: 53%|█████▎ | 1445/2703 [00:00<00:00, 2704.27it/s] word -> phonemes: 67%|██████▋ | 1812/2703 [00:00<00:00, 3008.65it/s] word -> phonemes: 78%|███████▊ | 2118/2703 [00:00<00:00, 2774.54it/s] word -> phonemes: 91%|█████████ | 2457/2703 [00:00<00:00, 2940.95it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2775.65it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 11%|█▏ | 307/2703 [00:00<00:00, 3044.11it/s] word -> phonemes: 23%|██▎ | 612/2703 [00:00<00:00, 2738.37it/s] word -> phonemes: 34%|███▎ | 907/2703 [00:00<00:00, 2726.76it/s] word -> phonemes: 44%|████▎ | 1181/2703 [00:00<00:00, 2546.87it/s] word -> phonemes: 54%|█████▍ | 1466/2703 [00:00<00:00, 2637.90it/s] word -> phonemes: 66%|██████▌ | 1783/2703 [00:00<00:00, 2808.29it/s] word -> phonemes: 80%|███████▉ | 2154/2703 [00:00<00:00, 3089.38it/s] word -> phonemes: 95%|█████████▍| 2559/2703 [00:00<00:00, 3369.71it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 3022.41it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 12%|█▏ | 431/3515 [00:00<00:00, 4309.50it/s] word -> phonemes: 26%|██▌ | 902/3515 [00:00<00:00, 4543.63it/s] word -> phonemes: 39%|███▊ | 1358/3515 [00:00<00:00, 4550.24it/s] word -> phonemes: 52%|█████▏ | 1814/3515 [00:00<00:00, 4427.89it/s] word -> phonemes: 64%|██████▍ | 2266/3515 [00:00<00:00, 4458.44it/s] word -> phonemes: 77%|███████▋ | 2713/3515 [00:00<00:00, 4443.78it/s] word -> phonemes: 90%|████████▉ | 3162/3515 [00:00<00:00, 4456.03it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4462.46it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 10%|▉ | 261/2703 [00:00<00:00, 2608.73it/s] word -> phonemes: 23%|██▎ | 616/2703 [00:00<00:00, 3109.07it/s] word -> phonemes: 36%|███▋ | 981/2703 [00:00<00:00, 3346.22it/s] word -> phonemes: 49%|████▉ | 1320/2703 [00:00<00:00, 3362.28it/s] word -> phonemes: 61%|██████▏ | 1657/2703 [00:00<00:00, 2792.89it/s] word -> phonemes: 72%|███████▏ | 1950/2703 [00:00<00:00, 2743.09it/s] word -> phonemes: 83%|████████▎ | 2233/2703 [00:00<00:00, 2539.76it/s] word -> phonemes: 95%|█████████▌| 2579/2703 [00:00<00:00, 2793.56it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 2736.33it/s] dev: 0%| | 0/2703 [00:00