preset parameters for DeepVoice3 + WaveNet

presets/deepvoice3_ljspeech_wavenet.json

@@ -0,0 +1,65 @@
+{
+  "name": "deepvoice3",
+  "frontend": "en",
+  "replace_pronunciation_prob": 0.5,
+  "builder": "deepvoice3",
+  "n_speakers": 1,
+  "speaker_embed_dim": 16,
+  "num_mels": 80,
+  "fmin": 125,
+  "fmax": 7600,
+  "fft_size": 1024,
+  "hop_size": 256,
+  "sample_rate": 22050,
+  "preemphasis": 0.0,
+  "min_level_db": -100,
+  "ref_level_db": 20,
+  "rescaling": true,
+  "rescaling_max": 0.999,
+  "allow_clipping_in_normalization": true,
+  "downsample_step": 1,
+  "outputs_per_step": 4,
+  "embedding_weight_std": 0.1,
+  "speaker_embedding_weight_std": 0.01,
+  "padding_idx": 0,
+  "max_positions": 2048,
+  "dropout": 0.050000000000000044,
+  "kernel_size": 3,
+  "text_embed_dim": 256,
+  "encoder_channels": 512,
+  "decoder_channels": 256,
+  "converter_channels": 256,
+  "query_position_rate": 1.0,
+  "key_position_rate": 1.385,
+  "key_projection": true,
+  "value_projection": false,
+  "use_memory_mask": true,
+  "trainable_positional_encodings": false,
+  "freeze_embedding": false,
+  "use_decoder_state_for_postnet_input": true,
+  "pin_memory": true,
+  "num_workers": 2,
+  "masked_loss_weight": 0.5,
+  "priority_freq": 3000,
+  "priority_freq_weight": 0.0,
+  "binary_divergence_weight": 0.1,
+  "use_guided_attention": true,
+  "guided_attention_sigma": 0.2,
+  "batch_size": 16,
+  "adam_beta1": 0.5,
+  "adam_beta2": 0.9,
+  "adam_eps": 1e-06,
+  "initial_learning_rate": 0.0005,
+  "lr_schedule": "noam_learning_rate_decay",
+  "lr_schedule_kwargs": {},
+  "nepochs": 2000,
+  "weight_decay": 0.0,
+  "clip_thresh": 0.1,
+  "checkpoint_interval": 10000,
+  "eval_interval": 10000,
+  "save_optimizer_state": true,
+  "force_monotonic_attention": true,
+  "window_ahead": 3,
+  "window_backward": 1,
+  "power": 1.4
+}