/content/project --2023-03-15 20:26:12-- https://huggingface.co/Uberduck/Aitch/resolve/main/aitch4.pt Resolving huggingface.co (huggingface.co)... 52.72.82.160, 23.20.207.15, 3.83.196.160, ... Connecting to huggingface.co (huggingface.co)|52.72.82.160|:443... connected. HTTP request sent, awaiting response... 302 Found Location: https://cdn-lfs.huggingface.co/repos/ac/1e/ac1e2ce25507ca44e65980f7de162a7a40390bb64463ff67e64a7a9e54ef4170/20f13029ea76fd17b4a194c6dff1d051ff73ebab1e6f40ec38581fc32c10973a?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27aitch4.pt%3B+filename%3D%22aitch4.pt%22%3B&Expires=1679170628&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly9jZG4tbGZzLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2FjLzFlL2FjMWUyY2UyNTUwN2NhNDRlNjU5ODBmN2RlMTYyYTdhNDAzOTBiYjY0NDYzZmY2N2U2NGE3YTllNTRlZjQxNzAvMjBmMTMwMjllYTc2ZmQxN2I0YTE5NGM2ZGZmMWQwNTFmZjczZWJhYjFlNmY0MGVjMzg1ODFmYzMyYzEwOTczYT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE2NzkxNzA2Mjh9fX1dfQ__&Signature=E7ycEc8PnbdAjhRzbittDBtK3f7XSdnTsib-6N6Neqz27rFzApX1C0OS3GWniuDwlX-XjQfs%7E9qXsyukz16i0TLvZBerWF5iNJ2bp2kVBSYXu9X36E4MKaPkxTH2eHgN4j4tCPtl%7Ek-RrdxeJKlvWHOkEXDgL785JzO65CCU-h%7E3BhEjKp85zhbcUHgQx3jSViNH%7EcwLImpds0RuQefFyXN%7ElYeJg9mdgNu8I4j4dTcKCbrH5UIHRkKHRP3kkdacnUuO-nHUG7VvWuGNyH9rPF3GReiLh0ja1AVRhItfU1nn2l485vVK9R8sUjKIiCktOpyUH6Rh1ERQ77yL4PrbCQ__&Key-Pair-Id=KVTP0A1DKRTAX [following] --2023-03-15 20:26:12-- https://cdn-lfs.huggingface.co/repos/ac/1e/ac1e2ce25507ca44e65980f7de162a7a40390bb64463ff67e64a7a9e54ef4170/20f13029ea76fd17b4a194c6dff1d051ff73ebab1e6f40ec38581fc32c10973a?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27aitch4.pt%3B+filename%3D%22aitch4.pt%22%3B&Expires=1679170628&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly9jZG4tbGZzLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2FjLzFlL2FjMWUyY2UyNTUwN2NhNDRlNjU5ODBmN2RlMTYyYTdhNDAzOTBiYjY0NDYzZmY2N2U2NGE3YTllNTRlZjQxNzAvMjBmMTMwMjllYTc2ZmQxN2I0YTE5NGM2ZGZmMWQwNTFmZjczZWJhYjFlNmY0MGVjMzg1ODFmYzMyYzEwOTczYT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoiLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE2NzkxNzA2Mjh9fX1dfQ__&Signature=E7ycEc8PnbdAjhRzbittDBtK3f7XSdnTsib-6N6Neqz27rFzApX1C0OS3GWniuDwlX-XjQfs%7E9qXsyukz16i0TLvZBerWF5iNJ2bp2kVBSYXu9X36E4MKaPkxTH2eHgN4j4tCPtl%7Ek-RrdxeJKlvWHOkEXDgL785JzO65CCU-h%7E3BhEjKp85zhbcUHgQx3jSViNH%7EcwLImpds0RuQefFyXN%7ElYeJg9mdgNu8I4j4dTcKCbrH5UIHRkKHRP3kkdacnUuO-nHUG7VvWuGNyH9rPF3GReiLh0ja1AVRhItfU1nn2l485vVK9R8sUjKIiCktOpyUH6Rh1ERQ77yL4PrbCQ__&Key-Pair-Id=KVTP0A1DKRTAX Resolving cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)... 13.249.85.23, 13.249.85.11, 13.249.85.116, ... Connecting to cdn-lfs.huggingface.co (cdn-lfs.huggingface.co)|13.249.85.23|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 118325723 (113M) [application/zip] Saving to: ‘/content/base_aitch.pt’ /content/base_aitch 100%[===================>] 112.84M 163MB/s in 0.7s 2023-03-15 20:26:13 (163 MB/s) - ‘/content/base_aitch.pt’ saved [118325723/118325723] [nltk_data] Downloading package averaged_perceptron_tagger to [nltk_data] /root/nltk_data... [nltk_data] Unzipping taggers/averaged_perceptron_tagger.zip. TTSTrainer start 5738.71633715 Initializing trainer with hparams: {'attention_dim': 128, 'attention_location_kernel_size': 31, 'attention_location_n_filters': 32, 'attention_rnn_dim': 1024, 'batch_size': 5, 'checkpoint_name': 'my-very-epic-model-deathwing', 'checkpoint_path': '/content/drive/MyDrive/tacotron', 'coarse_n_frames_per_step': None, 'config': 'tacotron2_config.json', 'cudnn_enabled': True, 'dataset_path': '.', 'debug': False, 'decay_rate': 8000, 'decay_start': 15000, 'decoder_rnn_dim': 1024, 'distributed_run': False, 'encoder_embedding_dim': 512, 'encoder_kernel_size': 5, 'encoder_n_convolutions': 3, 'epochs': 69420, 'epochs_per_checkpoint': 20, 'filter_length': 1024, 'fp16_run': False, 'gate_threshold': 0.5, 'grad_clip_thresh': 1.0, 'gst_dim': 2304, 'gst_type': 'torchmoji', 'has_speaker_embedding': True, 'hop_length': 256, 'ignore_layers': ['speaker_embedding.weight', 'spkr_lin.weight', 'spkr_lin.bias', 'embedding.weight'], 'include_f0': False, 'is_validate': True, 'learning_rate': 0.0007905694150420948, 'log_dir': '/content/project/logs', 'lrdecay_min': 7.905694150420948e-05, 'lrdecay_start': 150, 'lrdecay_steps': 350, 'mask_padding': True, 'max_decoder_steps': 1000, 'max_wav_value': 32768.0, 'mel_fmax': 8000, 'mel_fmin': 0, 'n_frames_per_step_initial': 1, 'n_mel_channels': 80, 'n_speakers': 1, 'num_heads': 8, 'p_arpabet': 0.0, 'p_attention_dropout': 0.1, 'p_decoder_dropout': 0.1, 'p_teacher_forcing': 1.0, 'pos_weight': None, 'postnet_embedding_dim': 512, 'postnet_kernel_size': 5, 'postnet_n_convolutions': 5, 'prenet_dim': 256, 'prenet_f0_dim': 1, 'prenet_f0_kernel_size': 1, 'prenet_f0_n_layers': 1, 'prenet_fms_kernel_size': 1, 'prenet_rms_dim': 0, 'reduction_window_schedule': [{'batch_size': 16, 'n_frames_per_step': 1, 'until_step': 10000}, {'batch_size': 16, 'n_frames_per_step': 1, 'until_step': 50000}, {'batch_size': 16, 'n_frames_per_step': 1, 'until_step': 60000}, {'batch_size': 16, 'n_frames_per_step': 1, 'until_step': 70000}, {'batch_size': 16, 'n_frames_per_step': 1, 'until_step': None}], 'ref_enc_filters': [32, 32, 64, 64, 128, 128], 'ref_enc_gru_size': 128, 'ref_enc_pad': [1, 1], 'ref_enc_size': [3, 3], 'ref_enc_strides': [2, 2], 'sample_inference_speaker_ids': [0], 'sample_inference_text': 'Я создал Драктиров!', 'sampling_rate': 22050, 'seed': 123, 'speaker_embedding_dim': 128, 'steps_per_sample': 50, 'symbol_set': 'russian', 'symbols_embedding_dim': 512, 'text_cleaners': ['basic_cleaners'], 'torchmoji_model_file': 'pytorch_model.bin', 'torchmoji_vocabulary_file': 'vocabulary.json', 'training_audiopaths_and_text': 'transcription.txt', 'val_audiopaths_and_text': 'transcription_val.txt', 'warm_start_name': '/content/base_aitch.pt', 'weight_decay': 1e-06, 'win_length': 1024, 'with_gst': True} /usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1475: UserWarning: nn.init.uniform is now deprecated in favor of nn.init.uniform_. nn.init.uniform(self.embed.weight.data, a=-0.5, b=0.5) /usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1477: UserWarning: nn.init.xavier_uniform is now deprecated in favor of nn.init.xavier_uniform_. nn.init.xavier_uniform(t) /usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1479: UserWarning: nn.init.orthogonal is now deprecated in favor of nn.init.orthogonal_. nn.init.orthogonal(t) /usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1481: UserWarning: nn.init.constant is now deprecated in favor of nn.init.constant_. nn.init.constant(t, 0) /usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/torchmoji.py:1483: UserWarning: nn.init.xavier_uniform is now deprecated in favor of nn.init.xavier_uniform_. nn.init.xavier_uniform(self.output_layer[0].weight.data) start train 5740.359279996 Initialized Torchmoji GST Starting warm_start 5750.803020147 WARNING! Attempting to load a model with out the embedding.weight layer. This could lead to unexpected results during evaluation. WARNING! Attempting to load a model with out the speaker_embedding.weight layer. This could lead to unexpected results during evaluation. Ending warm_start 5750.905390025 Error while getting data: ['speakers/0000_Deathwing/4.wav', 'Ты хорошо, служишь, господину.', '0'] shape '[1, 1, 252345]' is invalid for input of size 504690 Exception raised while training: shape '[1, 1, 252345]' is invalid for input of size 504690 Traceback (most recent call last): File "/usr/lib/python3.9/runpy.py", line 197, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.9/runpy.py", line 87, in _run_code exec(code, run_globals) File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/exec/train_tacotron2.py", line 49, in run(None, None, hparams) File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/exec/train_tacotron2.py", line 30, in run raise e File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/exec/train_tacotron2.py", line 26, in run trainer.train() File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/trainer/tacotron2.py", line 462, in train for batch_idx, batch in enumerate(train_loader): File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/dataloader.py", line 628, in __next__ data = self._next_data() File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/dataloader.py", line 671, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/_utils/fetch.py", line 58, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.9/dist-packages/torch/utils/data/_utils/fetch.py", line 58, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/data_loader.py", line 232, in __getitem__ data = self._get_data(self.audiopaths_and_text[idx]) File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/data_loader.py", line 207, in _get_data melspec = self.stft.mel_spectrogram(audio_norm) File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/common.py", line 397, in mel_spectrogram magnitudes, phases = self.stft_fn.transform(y) File "/usr/local/lib/python3.9/dist-packages/uberduck_ml_dev/models/common.py", line 251, in transform input_data = input_data.view(num_batches, 1, num_samples) RuntimeError: shape '[1, 1, 252345]' is invalid for input of size 504690