Upload 2 files

config.yml

@@ -0,0 +1,116 @@
+
+# This is the hyperparameter configuration file for Hifigan.
+# Please make sure this is adjusted for the LJSpeech dataset. If you want to
+# apply to the other dataset, you might need to carefully change some parameters.
+# This configuration performs 4000k iters.
+
+###########################################################
+#                FEATURE EXTRACTION SETTING               #
+###########################################################
+sampling_rate: 22050     # Sampling rate of dataset.
+hop_size: 256            # Hop size.
+format: "npy"
+
+
+###########################################################
+#         GENERATOR NETWORK ARCHITECTURE SETTING          #
+###########################################################
+model_type: "hifigan_generator"
+
+hifigan_generator_params:
+    out_channels: 1
+    kernel_size: 7
+    filters: 512
+    use_bias: true
+    upsample_scales: [8, 8, 2, 2]
+    stacks: 3
+    stack_kernel_size: [3, 7, 11]
+    stack_dilation_rate: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    use_final_nolinear_activation: true
+    is_weight_norm: false
+
+###########################################################
+#       DISCRIMINATOR NETWORK ARCHITECTURE SETTING        #
+###########################################################
+hifigan_discriminator_params:
+    out_channels: 1                     # Number of output channels (number of subbands).
+    period_scales: [2, 3, 5, 7, 11]     # List of period scales.
+    n_layers: 5                         # Number of layer of each period discriminator.
+    kernel_size: 5                      # Kernel size.
+    strides: 3                          # Strides
+    filters: 8                          # In Conv filters of each period discriminator
+    filter_scales: 4                    # Filter scales.
+    max_filters: 1024                   # maximum filters of period discriminator's conv.
+    is_weight_norm: false               # Use weight-norm or not.
+
+melgan_discriminator_params:
+    out_channels: 1                          # Number of output channels.
+    scales: 3                                # Number of multi-scales.
+    downsample_pooling: "AveragePooling1D"   # Pooling type for the input downsampling.
+    downsample_pooling_params:               # Parameters of the above pooling function.
+        pool_size: 4
+        strides: 2
+    kernel_sizes: [5, 3]              # List of kernel size.
+    filters: 16                       # Number of channels of the initial conv layer.
+    max_downsample_filters: 1024      # Maximum number of channels of downsampling layers.
+    downsample_scales: [4, 4, 4, 4]   # List of downsampling scales.
+    nonlinear_activation: "LeakyReLU" # Nonlinear activation function.
+    nonlinear_activation_params:      # Parameters of nonlinear activation function.
+        alpha: 0.2
+    is_weight_norm: false             # Use weight-norm or not.
+
+###########################################################
+#                   STFT LOSS SETTING                     #
+###########################################################
+stft_loss_params:
+    fft_lengths: [1024, 2048, 512]  # List of FFT size for STFT-based loss.
+    frame_steps: [120, 240, 50]     # List of hop size for STFT-based loss
+    frame_lengths: [600, 1200, 240] # List of window length for STFT-based loss.
+
+###########################################################
+#               ADVERSARIAL LOSS SETTING                  #
+###########################################################
+lambda_feat_match: 10.0
+lambda_adv: 4.0
+
+###########################################################
+#                  DATA LOADER SETTING                    #
+###########################################################
+batch_size: 16                 # Batch size for each GPU with assuming that gradient_accumulation_steps == 1.
+batch_max_steps: 8192          # Length of each audio in batch for training. Make sure dividable by hop_size.
+batch_max_steps_valid: 81920   # Length of each audio for validation. Make sure dividable by hope_size.
+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.
+is_shuffle: true               # shuffle dataset after each epoch.
+
+###########################################################
+#             OPTIMIZER & SCHEDULER SETTING               #
+###########################################################
+generator_optimizer_params:
+    lr_fn: "PiecewiseConstantDecay"
+    lr_params: 
+        boundaries: [100000, 200000, 300000, 400000, 500000, 600000, 700000]
+        values: [0.000125, 0.000125, 0.0000625, 0.0000625, 0.0000625, 0.00003125, 0.000015625, 0.000001]
+    amsgrad: false
+
+discriminator_optimizer_params:
+    lr_fn: "PiecewiseConstantDecay"
+    lr_params: 
+        boundaries: [100000, 200000, 300000, 400000, 500000]
+        values: [0.00025, 0.000125, 0.0000625, 0.00003125, 0.000015625, 0.000001]
+    amsgrad: false
+
+gradient_accumulation_steps: 1  # should be even number or 1.
+###########################################################
+#                    INTERVAL SETTING                     #
+###########################################################
+discriminator_train_start_steps: 100000  # steps begin training discriminator
+train_max_steps: 4000000                 # Number of training steps.
+save_interval_steps: 20000               # Interval steps to save checkpoint.
+eval_interval_steps: 5000                # Interval steps to evaluate the network.
+log_interval_steps: 200                  # Interval steps to record the training log.
+
+###########################################################
+#                     OTHER SETTING                       #
+###########################################################
+num_save_intermediate_results: 1  # Number of batch to be saved as intermediate results.

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c567276bfff1d64653d912fddaa3846554f924d7ba4146be039ec751f19f98a1
+size 55877376