Remove useless tests for speedup the aux_tests

tests/aux_tests/test_speaker_encoder_train.py

@@ -24,20 +24,21 @@ output_path = os.path.join(get_tests_output_path(), "train_outputs")
 
 config = SpeakerEncoderConfig(
     batch_size=4,
-    num_classes_in_batch=2,
+    num_classes_in_batch=4,
     num_utter_per_class=2,
-    eval_num_classes_in_batch=2,
+    eval_num_classes_in_batch=4,
     eval_num_utter_per_class=2,
     num_loader_workers=1,
-    epochs=2,
+    epochs=1,
     print_step=1,
-    save_step=1,
+    save_step=2,
     print_eval=True,
     run_eval=True,
     audio=BaseAudioConfig(num_mels=80),
 )
 config.audio.do_trim_silence = True
 config.audio.trim_db = 60
+config.loss = "ge2e"
 config.save_json(config_path)
 
 print(config)
@@ -72,14 +73,14 @@ run_cli(command_train)
 shutil.rmtree(continue_path)
 
 # test model with ge2e loss function
-config.loss = "ge2e"
-config.save_json(config_path)
-run_test_train()
+# config.loss = "ge2e"
+# config.save_json(config_path)
+# run_test_train()
 
 # test model with angleproto loss function
-config.loss = "angleproto"
-config.save_json(config_path)
-run_test_train()
+# config.loss = "angleproto"
+# config.save_json(config_path)
+# run_test_train()
 
 # test model with softmaxproto loss function
 config.loss = "softmaxproto"

tests/inputs/test_glow_tts.json

@@ -66,8 +66,8 @@
     "use_mas": false,       // use Monotonic Alignment Search if true. Otherwise use pre-computed attention alignments.
 
     // TRAINING
-    "batch_size": 2,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
-    "eval_batch_size":1,
+    "batch_size": 8,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
+    "eval_batch_size": 8,
     "r": 1,                 // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
     "loss_masking": true,   // enable / disable loss masking against the sequence padding.
     "data_dep_init_iter": 1,

tests/inputs/test_tacotron2_config.json

@@ -61,8 +61,8 @@
     "reinit_layers": [],    // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
 
     // TRAINING
-    "batch_size": 1,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
-    "eval_batch_size":1,
+    "batch_size": 8,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
+    "eval_batch_size": 8,
     "r": 7,                 // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
     "gradual_training": [[0, 7, 4], [1, 5, 2]], //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.

tests/inputs/test_tacotron_config.json

@@ -61,8 +61,8 @@
     "reinit_layers": [],    // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
 
     // TRAINING
-    "batch_size": 1,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
-    "eval_batch_size":1,
+    "batch_size": 8,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
+    "eval_batch_size": 8,
     "r": 7,                 // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
     "gradual_training": [[0, 7, 4], [1, 5, 2]], //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.