fix ton of tesnting bugs

tests/inputs/test_train_config.json

@@ -67,7 +67,7 @@
     "gradual_training": [[0, 7, 4]], //set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. For Tacotron, you might need to reduce the 'batch_size' as you proceeed.
     "loss_masking": true,         // enable / disable loss masking against the sequence padding.
     "ga_alpha": 10.0,        // weight for guided attention loss. If > 0, guided attention is enabled.
-    "apex_amp_level": null,
+    "mixed_precision": false,
 
     // VALIDATION
     "run_eval": true,
@@ -75,14 +75,15 @@
     "test_sentences_file": null,  // set a file to load sentences to be used for testing. If it is null then we use default english sentences.
 
     // LOSS SETTINGS
-    "loss_masking": false,       // enable / disable loss masking against the sequence padding.
-    "decoder_loss_alpha": 0.5,  // decoder loss weight. If > 0, it is enabled
-    "postnet_loss_alpha": 0.25, // postnet loss weight. If > 0, it is enabled
-    "ga_alpha": 10.0,           // weight for guided attention loss. If > 0, guided attention is enabled.
-    "decoder_diff_spec_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
+    "loss_masking": true,       // enable / disable loss masking against the sequence padding.
+    "decoder_loss_alpha": 0.5,  // original decoder loss weight. If > 0, it is enabled
+    "postnet_loss_alpha": 0.25, // original postnet loss weight. If > 0, it is enabled
     "postnet_diff_spec_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
-    "decoder_ssim_alpha": 0.5,     // differential spectral loss weight. If > 0, it is enabled
-    "postnet_ssim_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
+    "decoder_diff_spec_alpha": 0.25,     // differential spectral loss weight. If > 0, it is enabled
+    "decoder_ssim_alpha": 0.5,     // decoder ssim loss weight. If > 0, it is enabled
+    "postnet_ssim_alpha": 0.25,     // postnet ssim loss weight. If > 0, it is enabled
+    "ga_alpha": 5.0,           // weight for guided attention loss. If > 0, guided attention is enabled.
+    "stopnet_pos_weight": 15.0, // pos class weight for stopnet loss since there are way more negative samples than positive samples.
 
     // OPTIMIZER
     "noam_schedule": false,        // use noam warmup and lr schedule.

tests/inputs/test_vocoder_wavegrad.json

@@ -55,7 +55,8 @@
             [1, 2, 1, 2],
             [1, 2, 4, 8],
             [1, 2, 4, 8],
-            [1, 2, 4, 8]]
+            [1, 2, 4, 8]],
+        "use_weight_norm": true
     },
 
     // DATASET

tests/inputs/test_vocoder_wavernn_config.json

@@ -35,7 +35,7 @@
     },
 
     // Generating / Synthesizing
-    "batched": true,			
+    "batched": true,
     "target_samples": 11000,		// target number of samples to be generated in each batch entry
     "overlap_samples": 550,		// number of samples for crossfading between batches
 
@@ -53,12 +53,25 @@
     "mode": "mold",         		// mold [string], gauss [string], bits [int]
     "mulaw": false,         		// apply mulaw if mode is bits
     "padding": 2,			// pad the input for resnet to see wider input length
-    
+
     // DATASET
     //"use_gta": true,				// use computed gta features from the tts model
     "data_path": "tests/data/ljspeech/wavs/",	// path containing training wav files
     "feature_path": null, 			// path containing computed features from wav files if null compute them
 
+    // MODEL PARAMETERS
+    "wavernn_model_params": {
+        "rnn_dims": 512,
+        "fc_dims": 512,
+        "compute_dims": 128,
+        "res_out_dims": 128,
+        "num_res_blocks": 10,
+        "use_aux_net": true,
+        "use_upsample_net": true,
+        "upsample_factors": [4, 8, 8] 	// this needs to correctly factorise hop_length
+    },
+    "mixed_precision": false,
+
     // TRAINING
     "batch_size": 4,       	// Batch size for training. Lower values than 32 might cause hard to learn attention.
     "epochs": 1,        	// total number of epochs to train.
@@ -86,7 +99,7 @@
     // DATA LOADING
     "num_loader_workers": 4,        // number of training data loader processes. Don't set it too big. 4-8 are good values.
     "num_val_loader_workers": 4,    // number of evaluation data loader processes.
-    "eval_split_size": 10,	    // number of samples for testing	
+    "eval_split_size": 10,	    // number of samples for testing
 
     // PATHS
     "output_path": "tests/train_outputs/"