Rename more

TTS/bin/eval_encoder.py

@@ -56,7 +56,7 @@ if __name__ == "__main__":
         description="""Compute the accuracy of the encoder.\n\n"""
         """
         Example runs:
-        python TTS/bin/eval_encoder.py emotion_encoder_model.pth.tar emotion_encoder_config.json  dataset_config.json
+        python TTS/bin/eval_encoder.py emotion_encoder_model.pth emotion_encoder_config.json  dataset_config.json
         """,
         formatter_class=RawTextHelpFormatter,
     )

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)

TTS/utils/manage.py

@@ -114,7 +114,7 @@ class ModelManager(object):
             e.g. 'tts_model/en/ljspeech/tacotron'
 
         Every model must have the following files:
-            - *.pth.tar : pytorch model checkpoint file.
+            - *.pth : pytorch model checkpoint file.
             - config.json : model config file.
             - scale_stats.npy (if exist): scale values for preprocessing.
 
@@ -127,7 +127,7 @@ class ModelManager(object):
         model_item = self.models_dict[model_type][lang][dataset][model]
         # set the model specific output path
         output_path = os.path.join(self.output_prefix, model_full_name)
-        output_model_path = os.path.join(output_path, "model_file.pth.tar")
+        output_model_path = os.path.join(output_path, "model_file.pth")
         output_config_path = os.path.join(output_path, "config.json")
 
         if os.path.exists(output_path):
@@ -152,7 +152,7 @@ class ModelManager(object):
         output_d_vector_file_path = os.path.join(output_path, "speakers.json")
         output_speaker_ids_file_path = os.path.join(output_path, "speaker_ids.json")
         speaker_encoder_config_path = os.path.join(output_path, "config_se.json")
-        speaker_encoder_model_path = os.path.join(output_path, "model_se.pth.tar")
+        speaker_encoder_model_path = os.path.join(output_path, "model_se.pth")
 
         # update the scale_path.npy file path in the model config.json
         self._update_path("audio.stats_path", output_stats_path, config_path)