wavegrad refactoring, fixing tests for glow-tts and wavegrad

tests/test_encoder.py

@@ -62,7 +62,7 @@ class GE2ELossTests(unittest.TestCase):
         assert output.item() >= 0.0
         # check speaker loss with orthogonal d-vectors
         dummy_input = T.empty(3, 64)
-        dummy_input = T.nn.init.orthogonal(dummy_input)
+        dummy_input = T.nn.init.orthogonal_(dummy_input)
         dummy_input = T.cat(
             [
                 dummy_input[0].repeat(5, 1, 1).transpose(0, 1),
@@ -91,7 +91,7 @@ class AngleProtoLossTests(unittest.TestCase):
 
         # check speaker loss with orthogonal d-vectors
         dummy_input = T.empty(3, 64)
-        dummy_input = T.nn.init.orthogonal(dummy_input)
+        dummy_input = T.nn.init.orthogonal_(dummy_input)
         dummy_input = T.cat(
             [
                 dummy_input[0].repeat(5, 1, 1).transpose(0, 1),

tests/test_server_package.sh

@@ -6,12 +6,12 @@ if [[ ! -f tests/outputs/checkpoint_10.pth.tar ]]; then
     exit 1
 fi
 
+rm -f dist/*.whl
+python setup.py --quiet bdist_wheel --checkpoint tests/outputs/checkpoint_10.pth.tar --model_config tests/outputs/dummy_model_config.json
+
 python -m venv /tmp/venv
 source /tmp/venv/bin/activate
 pip install --quiet --upgrade pip setuptools wheel
-
-rm -f dist/*.whl
-python setup.py --quiet bdist_wheel --checkpoint tests/outputs/checkpoint_10.pth.tar --model_config tests/outputs/dummy_model_config.json
 pip install --quiet dist/TTS*.whl
 
 # this is related to https://github.com/librosa/librosa/issues/1160

tests/test_wavegrad_train.py

@@ -30,9 +30,18 @@ class WavegradTrainTest(unittest.TestCase):
                      upsample_dilations=[[1, 2, 1, 2], [1, 2, 1, 2],
                                          [1, 2, 4, 8], [1, 2, 4, 8],
                                          [1, 2, 4, 8]])
+
+        model_ref = Wavegrad(in_channels=80,
+                     out_channels=1,
+                     upsample_factors=[5, 5, 3, 2, 2],
+                     upsample_dilations=[[1, 2, 1, 2], [1, 2, 1, 2],
+                                         [1, 2, 4, 8], [1, 2, 4, 8],
+                                         [1, 2, 4, 8]])
         model.train()
         model.to(device)
-        model_ref = copy.deepcopy(model)
+        model.compute_noise_level(1000, 1e-6, 1e-2)
+        model_ref.load_state_dict(model.state_dict())
+        model_ref.to(device)
         count = 0
         for param, param_ref in zip(model.parameters(),
                                     model_ref.parameters()):