/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: 11%|█ | 371/3515 [00:00<00:00, 3704.70it/s] word -> phonemes: 21%|██ | 742/3515 [00:00<00:00, 3451.69it/s] word -> phonemes: 33%|███▎ | 1151/3515 [00:00<00:00, 3731.60it/s] word -> phonemes: 44%|████▍ | 1556/3515 [00:00<00:00, 3852.82it/s] word -> phonemes: 55%|█████▌ | 1943/3515 [00:00<00:00, 3722.57it/s] word -> phonemes: 67%|██████▋ | 2346/3515 [00:00<00:00, 3821.28it/s] word -> phonemes: 79%|███████▊ | 2766/3515 [00:00<00:00, 3940.87it/s] word -> phonemes: 90%|█████████ | 3165/3515 [00:00<00:00, 3955.38it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 3869.31it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 13%|█▎ | 362/2703 [00:00<00:00, 3617.79it/s] word -> phonemes: 32%|███▏ | 876/2703 [00:00<00:00, 4508.64it/s] word -> phonemes: 51%|█████ | 1370/2703 [00:00<00:00, 4703.32it/s] word -> phonemes: 68%|██████▊ | 1841/2703 [00:00<00:00, 4673.84it/s] word -> phonemes: 86%|████████▌ | 2317/2703 [00:00<00:00, 4704.10it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4598.22it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▉ | 509/2703 [00:00<00:00, 5085.92it/s] word -> phonemes: 38%|███▊ | 1018/2703 [00:00<00:00, 4885.94it/s] word -> phonemes: 57%|█████▋ | 1542/2703 [00:00<00:00, 5041.98it/s] word -> phonemes: 77%|███████▋ | 2077/2703 [00:00<00:00, 5161.73it/s] word -> phonemes: 96%|█████████▌| 2594/2703 [00:00<00:00, 4863.57it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4917.55it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 17%|█▋ | 463/2703 [00:00<00:00, 4626.51it/s] word -> phonemes: 37%|███▋ | 1007/2703 [00:00<00:00, 5060.68it/s] word -> phonemes: 56%|█████▌ | 1513/2703 [00:00<00:00, 4738.44it/s] word -> phonemes: 74%|███████▎ | 1989/2703 [00:00<00:00, 4475.38it/s] word -> phonemes: 91%|█████████▏| 2469/2703 [00:00<00:00, 4584.55it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4689.30it/s] dev: 0%| | 0/2703 [00:00 phonemes: 0%| | 0/3515 [00:00 phonemes: 10%|█ | 368/3515 [00:00<00:00, 3679.37it/s] word -> phonemes: 22%|██▏ | 771/3515 [00:00<00:00, 3883.17it/s] word -> phonemes: 35%|███▌ | 1234/3515 [00:00<00:00, 4221.02it/s] word -> phonemes: 48%|████▊ | 1675/3515 [00:00<00:00, 4292.69it/s] word -> phonemes: 61%|██████▏ | 2158/3515 [00:00<00:00, 4484.17it/s] word -> phonemes: 74%|███████▍ | 2607/3515 [00:00<00:00, 4154.10it/s] word -> phonemes: 86%|████████▌ | 3027/3515 [00:00<00:00, 4030.83it/s] word -> phonemes: 98%|█████████▊| 3434/3515 [00:00<00:00, 3958.63it/s] word -> phonemes: 100%|██████████| 3515/3515 [00:00<00:00, 4031.50it/s] train: 0%| | 0/3515 [00:00 phonemes: 0%| | 0/2703 [00:00 phonemes: 19%|█▉ | 517/2703 [00:00<00:00, 5162.20it/s] word -> phonemes: 38%|███▊ | 1034/2703 [00:00<00:00, 4533.62it/s] word -> phonemes: 58%|█████▊ | 1573/2703 [00:00<00:00, 4896.75it/s] word -> phonemes: 77%|███████▋ | 2069/2703 [00:00<00:00, 4805.96it/s] word -> phonemes: 96%|█████████▌| 2600/2703 [00:00<00:00, 4978.06it/s] word -> phonemes: 100%|██████████| 2703/2703 [00:00<00:00, 4831.87it/s] dev: 0%| | 0/2703 [00:00