Closed FurkanGozukara closed 1 year ago
I am trying to run 12-48 / aero-nfft=512-hl=256 Although I have no idea what is 512 and 256
installed all requirements
run my command like this and got error
python predict.py dset=4-16 experiment=aero_4-16_512_256 +filename="D:\86 se courses youtube kanali\aero\5dk.mp3" +output="D:\86 se courses youtube kanali\aero\5_v2dk.mp3" checkpoint_file="D:\86 se courses youtube kanali\aero\checkpoint.th"
I want to improve quality of this audio 5 min sound : https://sndup.net/stjs/
(env) D:\86 se courses youtube kanali\aero>python predict.py dset=4-16 experiment=aero_4-16_512_256 +filename="D:\86 se courses youtube kanali\aero\5dk.mp3" +output="D:\86 se courses youtube kanali\aero\5_v2dk.mp3" checkpoint_file="D:\86 se courses youtube kanali\aero\checkpoint.th" D:\86 se courses youtube kanali\aero\env\lib\site-packages\hydra\_internal\defaults_list.py:251: UserWarning: In 'main_config': Defaults list is missing `_self_`. See https://hydra.cc/docs/upgrades/1.0_to_1.1/default_composition_order for more information warnings.warn(msg, UserWarning) {'experiment': {'name': 'aero-nfft=${experiment.nfft}-hl=${experiment.hop_length}', 'lr_sr': 4000, 'hr_sr': 16000, 'segment': 2, 'stride': 2, 'pad': True, 'upsample': False, 'batch_size': 16, 'nfft': 512, 'hop_length': 256, 'model': 'aero', 'aero': {'in_channels': 1, 'out_channels': 1, 'channels': 48, 'growth': 2, 'nfft': '${experiment.nfft}', 'hop_length': '${experiment.hop_length}', 'end_iters': 0, 'cac': True, 'rewrite': True, 'hybrid': False, 'hybrid_old': False, 'freq_emb': 0.2, 'emb_scale': 10, 'emb_smooth': True, 'kernel_size': 8, 'strides': [4, 4, 2, 2], 'context': 1, 'context_enc': 0, 'freq_ends': 4, 'enc_freq_attn': 0, 'norm_starts': 2, 'norm_groups': 4, 'dconv_mode': 1, 'dconv_depth': 2, 'dconv_comp': 4, 'dconv_time_attn': 2, 'dconv_lstm': 2, 'dconv_init': 0.001, 'rescale': 0.1, 'lr_sr': '${experiment.lr_sr}', 'hr_sr': '${experiment.hr_sr}', 'spec_upsample': True, 'act_func': 'snake', 'debug': False}, 'adversarial': True, 'features_loss_lambda': 100, 'only_features_loss': False, 'only_adversarial_loss': False, 'discriminator_models': ['msd_melgan'], 'melgan_discriminator': {'n_layers': 4, 'num_D': 3, 'downsampling_factor': 4, 'ndf': 16}}, 'dset': {'name': '4-16', 'train': 'egs/vctk/4-16/tr', 'valid': None, 'test': 'egs/vctk/4-16/val'}, 'num_prints': 5, 'device': 'cuda', 'num_workers': 2, 'verbose': 0, 'show': 0, 'log_results': True, 'checkpoint': True, 'continue_from': '', 'continue_best': False, 'restart': False, 'checkpoint_file': 'D:\\86 se courses youtube kanali\\aero\\checkpoint.th', 'best_file': 'best.th', 'history_file': 'history.json', 'test_results_file': 'test_results.json', 'samples_dir': 'samples', 'keep_history': True, 'seed': 2036, 'dummy': '', 'visqol': True, 'visqol_path': None, 'eval_every': 25, 'enhance_samples_limit': -1, 'valid_equals_test': None, 'cross_valid': False, 'cross_valid_every': 5, 'joint_evaluate_and_enhance': True, 'evaluate_on_best': False, 'wandb': {'project_name': 'Spectral Bandwidth Extension', 'entity': None, 'mode': 'online', 'log': 'all', 'log_freq': 5, 'n_files_to_log': 10, 'n_files_to_log_to_table': 10, 'tags': [], 'resume': False}, 'optim': 'adam', 'lr': 0.0003, 'beta1': 0.8, 'beta2': 0.999, 'losses': ['stft'], 'stft_sc_factor': 0.5, 'stft_mag_factor': 0.5, 'epochs': 125, 'ddp': False, 'ddp_backend': 'nccl', 'rendezvous_file': './rendezvous', 'rank': None, 'world_size': None, 'filename': 'D:\\86 se courses youtube kanali\\aero\\5dk.mp3', 'output': 'D:\\86 se courses youtube kanali\\aero\\5_v2dk.mp3'} [2023-02-09 14:36:36,703][__main__][INFO] - Loading model aero from last state. [2023-02-09 14:36:38,679][__main__][INFO] - lr wav shape: torch.Size([2, 14400000]) [2023-02-09 14:36:38,680][__main__][INFO] - number of chunks: 30 Error executing job with overrides: ['dset=4-16', 'experiment=aero_4-16_512_256', '+filename=D:\\86 se courses youtube kanali\\aero\\5dk.mp3', '+output=D:\\86 se courses youtube kanali\\aero\\5_v2dk.mp3', 'checkpoint_file=D:\\86 se courses youtube kanali\\aero\\checkpoint.th'] Traceback (most recent call last): File "D:\86 se courses youtube kanali\aero\predict.py", line 77, in main pr_chunk = model(lr_chunk.unsqueeze(0).to(device)).squeeze(0) File "D:\86 se courses youtube kanali\aero\env\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "D:\86 se courses youtube kanali\aero\src\models\aero.py", line 472, in forward x = encode(x, inject) File "D:\86 se courses youtube kanali\aero\env\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "D:\86 se courses youtube kanali\aero\src\models\aero.py", line 120, in forward x = self.pre_conv(x) File "D:\86 se courses youtube kanali\aero\env\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "D:\86 se courses youtube kanali\aero\env\lib\site-packages\torch\nn\modules\conv.py", line 457, in forward return self._conv_forward(input, self.weight, self.bias) File "D:\86 se courses youtube kanali\aero\env\lib\site-packages\torch\nn\modules\conv.py", line 453, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: Given groups=1, weight of size [48, 2, 1, 1], expected input[1, 4, 256, 7501] to have 2 channels, but got 4 channels instead Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
Your audio should be mono, is it mono (single channel) or stereo (2 channels)? If it is not mono, you should convert it to mono (you can use any tool e.g. sox, ffmpeg).
I am trying to run 12-48 / aero-nfft=512-hl=256 Although I have no idea what is 512 and 256
installed all requirements
run my command like this and got error
python predict.py dset=4-16 experiment=aero_4-16_512_256 +filename="D:\86 se courses youtube kanali\aero\5dk.mp3" +output="D:\86 se courses youtube kanali\aero\5_v2dk.mp3" checkpoint_file="D:\86 se courses youtube kanali\aero\checkpoint.th"
I want to improve quality of this audio 5 min sound : https://sndup.net/stjs/