update dummy model config

tests/outputs/dummy_model_config.json

@@ -4,7 +4,7 @@
 
     "audio":{
         // Audio processing parameters
-        "num_mels": 80,         // size of the mel spec frame. 
+        "num_mels": 80,         // size of the mel spec frame.
         "num_freq": 1025,       // number of stft frequency levels. Size of the linear spectogram frame.
         "sample_rate": 22050,   // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
         "frame_length_ms": 50,  // stft window length in ms.
@@ -31,19 +31,19 @@
 
     "reinit_layers": [],
 
-    "model": "Tacotron2",          // one of the model in models/    
+    "model": "Tacotron2",          // one of the model in models/
     "grad_clip": 1,                // upper limit for gradients for clipping.
     "epochs": 1000,                // total number of epochs to train.
     "lr": 0.0001,                  // Initial learning rate. If Noam decay is active, maximum learning rate.
     "lr_decay": false,             // if true, Noam learning rate decaying is applied through training.
     "warmup_steps": 4000,          // Noam decay steps to increase the learning rate from 0 to "lr"
     "windowing": false,            // Enables attention windowing. Used only in eval mode.
-    "memory_size": 5,              // ONLY TACOTRON - memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5. 
+    "memory_size": 5,              // ONLY TACOTRON - memory queue size used to queue network predictions to feed autoregressive connection. Useful if r < 5.
     "attention_norm": "sigmoid",   // softmax or sigmoid. Suggested to use softmax for Tacotron2 and sigmoid for Tacotron.
     "prenet_type": "original",     // ONLY TACOTRON2 - "original" or "bn".
-    "prenet_dropout": true,        // ONLY TACOTRON2 - enable/disable dropout at prenet. 
+    "prenet_dropout": true,        // ONLY TACOTRON2 - enable/disable dropout at prenet.
     "use_forward_attn": true,      // ONLY TACOTRON2 - if it uses forward attention. In general, it aligns faster.
-    "forward_attn_mask": false, 
+    "forward_attn_mask": false,
     "attention_type": "original",
     "attention_heads": 5,
     "bidirectional_decoder": false,
@@ -51,13 +51,15 @@
     "location_attn": false,        // ONLY TACOTRON2 - enable_disable location sensitive attention. It is enabled for TACOTRON by default.
     "loss_masking": true,         // enable / disable loss masking against the sequence padding.
     "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
-    "stopnet": true,               // Train stopnet predicting the end of synthesis. 
+    "stopnet": true,               // Train stopnet predicting the end of synthesis.
     "separate_stopnet": true,     // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER.
     "tb_model_param_stats": false,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
-    "use_gst": false, 
-    
+    "use_gst": false,
+    "double_decoder_consistency": true,  // use DDC explained here https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency-draft/
+    "ddc_r": 7,                           // reduction rate for coarse decoder.
+
     "batch_size": 32,       // Batch size for training. Lower values than 32 might cause hard to learn attention.
-    "eval_batch_size":16,   
+    "eval_batch_size":16,
     "r": 1,                 // Number of frames to predict for step.
     "wd": 0.000001,         // Weight decay weight.
     "checkpoint": true,     // If true, it saves checkpoints per "save_step"