From afe9d4a4f16f8cdd54c2d61afec4c6696931e6a4 Mon Sep 17 00:00:00 2001 From: chenfeiyu Date: Wed, 30 Jun 2021 14:20:06 +0800 Subject: [PATCH] delete config for paralle training --- .../parallelwave_gan/baker/conf/parallel.yaml | 127 ------------------ 1 file changed, 127 deletions(-) delete mode 100644 examples/parallelwave_gan/baker/conf/parallel.yaml diff --git a/examples/parallelwave_gan/baker/conf/parallel.yaml b/examples/parallelwave_gan/baker/conf/parallel.yaml deleted file mode 100644 index f23b243..0000000 --- a/examples/parallelwave_gan/baker/conf/parallel.yaml +++ /dev/null @@ -1,127 +0,0 @@ -# This is the hyperparameter configuration file for Parallel WaveGAN. -# Please make sure this is adjusted for the CSMSC dataset. If you want to -# apply to the other dataset, you might need to carefully change some parameters. -# This configuration requires 12 GB GPU memory and takes ~3 days on RTX TITAN. - -########################################################### -# FEATURE EXTRACTION SETTING # -########################################################### -sr: 24000 # Sampling rate. -n_fft: 2048 # FFT size. -hop_length: 300 # Hop size. -win_length: 1200 # Window length. - # If set to null, it will be the same as fft_size. -window: "hann" # Window function. -n_mels: 80 # Number of mel basis. -fmin: 80 # Minimum freq in mel basis calculation. -fmax: 7600 # Maximum frequency in mel basis calculation. -# global_gain_scale: 1.0 # Will be multiplied to all of waveform. -trim_silence: false # Whether to trim the start and end of silence. -top_db: 60 # Need to tune carefully if the recording is not good. -trim_frame_length: 2048 # Frame size in trimming. -trim_hop_length: 512 # Hop size in trimming. -# format: "npy" # Feature file format. "npy" or "hdf5" is supported. - -########################################################### -# GENERATOR NETWORK ARCHITECTURE SETTING # -########################################################### -generator_params: - in_channels: 1 # Number of input channels. - out_channels: 1 # Number of output channels. - kernel_size: 3 # Kernel size of dilated convolution. - layers: 30 # Number of residual block layers. - stacks: 3 # Number of stacks i.e., dilation cycles. - residual_channels: 64 # Number of channels in residual conv. - gate_channels: 128 # Number of channels in gated conv. - skip_channels: 64 # Number of channels in skip conv. - aux_channels: 80 # Number of channels for auxiliary feature conv. - # Must be the same as num_mels. - aux_context_window: 2 # Context window size for auxiliary feature. - # If set to 2, previous 2 and future 2 frames will be considered. - dropout: 0.0 # Dropout rate. 0.0 means no dropout applied. - bias: true # use bias in residual blocks - use_weight_norm: true # Whether to use weight norm. - # If set to true, it will be applied to all of the conv layers. - use_causal_conv: false # use causal conv in residual blocks and upsample layers - # upsample_net: "ConvInUpsampleNetwork" # Upsampling network architecture. - upsample_scales: [4, 5, 3, 5] # Upsampling scales. Prodcut of these must be the same as hop size. - interpolate_mode: "nearest" # upsample net interpolate mode - freq_axis_kernel_size: 1 # upsamling net: convolution kernel size in frequencey axis - nonlinear_activation: null - nonlinear_activation_params: {} - -########################################################### -# DISCRIMINATOR NETWORK ARCHITECTURE SETTING # -########################################################### -discriminator_params: - in_channels: 1 # Number of input channels. - out_channels: 1 # Number of output channels. - kernel_size: 3 # Number of output channels. - layers: 10 # Number of conv layers. - conv_channels: 64 # Number of chnn layers. - bias: true # Whether to use bias parameter in conv. - use_weight_norm: true # Whether to use weight norm. - # If set to true, it will be applied to all of the conv layers. - nonlinear_activation: "LeakyReLU" # Nonlinear function after each conv. - nonlinear_activation_params: # Nonlinear function parameters - negative_slope: 0.2 # Alpha in LeakyReLU. - -########################################################### -# STFT LOSS SETTING # -########################################################### -stft_loss_params: - fft_sizes: [1024, 2048, 512] # List of FFT size for STFT-based loss. - hop_sizes: [120, 240, 50] # List of hop size for STFT-based loss - win_lengths: [600, 1200, 240] # List of window length for STFT-based loss. - window: "hann" # Window function for STFT-based loss - -########################################################### -# ADVERSARIAL LOSS SETTING # -########################################################### -lambda_adv: 4.0 # Loss balancing coefficient. - -########################################################### -# DATA LOADER SETTING # -########################################################### -batch_size: 6 # Batch size. -batch_max_steps: 25500 # Length of each audio in batch. Make sure dividable by hop_size. -pin_memory: true # Whether to pin memory in Pytorch DataLoader. -num_workers: 4 # Number of workers in Pytorch DataLoader. -remove_short_samples: true # Whether to remove samples the length of which are less than batch_max_steps. -allow_cache: true # Whether to allow cache in dataset. If true, it requires cpu memory. - -########################################################### -# OPTIMIZER & SCHEDULER SETTING # -########################################################### -generator_optimizer_params: - epsilon: 1.0e-6 # Generator's epsilon. - weight_decay: 0.0 # Generator's weight decay coefficient. -generator_scheduler_params: - learning_rate: 0.0001 # Generator's learning rate. - step_size: 100000 # Generator's scheduler step size. - gamma: 0.5 # Generator's scheduler gamma. - # At each step size, lr will be multiplied by this parameter. -generator_grad_norm: 10 # Generator's gradient norm. -discriminator_optimizer_params: - epsilon: 1.0e-6 # Discriminator's epsilon. - weight_decay: 0.0 # Discriminator's weight decay coefficient. -discriminator_scheduler_params: - learning_rate: 0.00005 # Discriminator's learning rate. - step_size: 100000 # Discriminator's scheduler step size. - gamma: 0.5 # Discriminator's scheduler gamma. - # At each step size, lr will be multiplied by this parameter. -discriminator_grad_norm: 1 # Discriminator's gradient norm. - -########################################################### -# INTERVAL SETTING # -########################################################### -discriminator_train_start_steps: 50000 # Number of steps to start to train discriminator. -train_max_steps: 400000 # Number of training steps. -save_interval_steps: 5000 # Interval steps to save checkpoint. -eval_interval_steps: 1000 # Interval steps to evaluate the network. -log_interval_steps: 100 # Interval steps to record the training log. - -########################################################### -# OTHER SETTING # -########################################################### -num_save_intermediate_results: 4 # Number of results to be saved as intermediate results.