Update model file extension (#1422)

* Update model file ext to ```.pth```

* Update docs

* Rename more

* Find model files

TTS/encoder/README.md

@@ -14,5 +14,5 @@ To run the code, you need to follow the same flow as in TTS.
 
 - Define 'config.json' for your needs. Note that, audio parameters should match your TTS model.
 - Example training call ```python speaker_encoder/train.py --config_path speaker_encoder/config.json --data_path ~/Data/Libri-TTS/train-clean-360```
-- Generate embedding vectors ```python speaker_encoder/compute_embeddings.py --use_cuda true /model/path/best_model.pth.tar model/config/path/config.json dataset/path/ output_path``` . This code parses all .wav files at the given dataset path and generates the same folder structure under the output path with the generated embedding files.
+- Generate embedding vectors ```python speaker_encoder/compute_embeddings.py --use_cuda true /model/path/best_model.pth model/config/path/config.json dataset/path/ output_path``` . This code parses all .wav files at the given dataset path and generates the same folder structure under the output path with the generated embedding files.
 - Watch training on Tensorboard as in TTS

TTS/encoder/utils/generic_utils.py

@@ -147,7 +147,7 @@ def setup_speaker_encoder_model(config: "Coqpit"):
 
 
 def save_checkpoint(model, optimizer, criterion, model_loss, out_path, current_step, epoch):
-    checkpoint_path = "checkpoint_{}.pth.tar".format(current_step)
+    checkpoint_path = "checkpoint_{}.pth".format(current_step)
     checkpoint_path = os.path.join(out_path, checkpoint_path)
     print(" | | > Checkpoint saving : {}".format(checkpoint_path))
 
@@ -177,7 +177,7 @@ def save_best_model(model, optimizer, criterion, model_loss, best_loss, out_path
             "date": datetime.date.today().strftime("%B %d, %Y"),
         }
         best_loss = model_loss
-        bestmodel_path = "best_model.pth.tar"
+        bestmodel_path = "best_model.pth"
         bestmodel_path = os.path.join(out_path, bestmodel_path)
         print("\n > BEST MODEL ({0:.5f}) : {1:}".format(model_loss, bestmodel_path))
         save_fsspec(state, bestmodel_path)

TTS/encoder/utils/io.py

@@ -5,7 +5,7 @@ from TTS.utils.io import save_fsspec
 
 
 def save_checkpoint(model, optimizer, model_loss, out_path, current_step):
-    checkpoint_path = "checkpoint_{}.pth.tar".format(current_step)
+    checkpoint_path = "checkpoint_{}.pth".format(current_step)
     checkpoint_path = os.path.join(out_path, checkpoint_path)
     print(" | | > Checkpoint saving : {}".format(checkpoint_path))
 
@@ -31,7 +31,7 @@ def save_best_model(model, optimizer, model_loss, best_loss, out_path, current_s
             "date": datetime.date.today().strftime("%B %d, %Y"),
         }
         best_loss = model_loss
-        bestmodel_path = "best_model.pth.tar"
+        bestmodel_path = "best_model.pth"
         bestmodel_path = os.path.join(out_path, bestmodel_path)
         print("\n > BEST MODEL ({0:.5f}) : {1:}".format(model_loss, bestmodel_path))
         save_fsspec(state, bestmodel_path)