Update model file extension (#1422)

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

* Update docs

* Rename more

* Find model files

Author: erogol

.gitignore

@@ -115,6 +115,7 @@ venv.bak/
 *.swo
 
 # pytorch models
+*.pth
 *.pth.tar
 result/
 

README.md

@@ -159,13 +159,13 @@ If you are on Windows, 👑@GuyPaddock wrote installation instructions [here](ht
 - Run your own TTS model (Using Griffin-Lim Vocoder):
 
     ```
-    $ tts --text "Text for TTS" --model_path path/to/model.pth.tar --config_path path/to/config.json --out_path output/path/speech.wav
+    $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav
     ```
 
 - Run your own TTS and Vocoder models:
     ```
-    $ tts --text "Text for TTS" --model_path path/to/config.json --config_path path/to/model.pth.tar --out_path output/path/speech.wav
-        --vocoder_path path/to/vocoder.pth.tar --vocoder_config_path path/to/vocoder_config.json
+    $ tts --text "Text for TTS" --model_path path/to/config.json --config_path path/to/model.pth --out_path output/path/speech.wav
+        --vocoder_path path/to/vocoder.pth --vocoder_config_path path/to/vocoder_config.json
     ```
 
 ### Multi-speaker Models
@@ -185,7 +185,7 @@ If you are on Windows, 👑@GuyPaddock wrote installation instructions [here](ht
 - Run your own multi-speaker TTS model:
 
     ```
-    $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/config.json --config_path path/to/model.pth.tar --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
+    $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/config.json --config_path path/to/model.pth --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
     ```
 
 ## Directory Structure

TTS/bin/compute_attention_masks.py

@@ -25,7 +25,7 @@
         """
 Example run:
     CUDA_VISIBLE_DEVICE="0" python TTS/bin/compute_attention_masks.py
-        --model_path /data/rw/home/Models/ljspeech-dcattn-December-14-2020_11+10AM-9d0e8c7/checkpoint_200000.pth.tar
+        --model_path /data/rw/home/Models/ljspeech-dcattn-December-14-2020_11+10AM-9d0e8c7/checkpoint_200000.pth
         --config_path /data/rw/home/Models/ljspeech-dcattn-December-14-2020_11+10AM-9d0e8c7/config.json
         --dataset_metafile metadata.csv
         --data_path /root/LJSpeech-1.1/

TTS/bin/compute_embeddings.py

@@ -12,7 +12,7 @@
     description="""Compute embedding vectors for each wav file in a dataset.\n\n"""
     """
     Example runs:
-    python TTS/bin/compute_embeddings.py speaker_encoder_model.pth.tar speaker_encoder_config.json  dataset_config.json embeddings_output_path/
+    python TTS/bin/compute_embeddings.py speaker_encoder_model.pth speaker_encoder_config.json  dataset_config.json embeddings_output_path/
     """,
     formatter_class=RawTextHelpFormatter,
 )

TTS/bin/distribute.py

@@ -56,7 +56,7 @@ def compute_encoder_accuracy(dataset_items, encoder_manager):
         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/bin/eval_encoder.py

@@ -60,13 +60,13 @@ def main():
 - Run your own TTS model (Using Griffin-Lim Vocoder):
 
     ```
-    $ tts --text "Text for TTS" --model_path path/to/model.pth.tar --config_path path/to/config.json --out_path output/path/speech.wav
+    $ tts --text "Text for TTS" --model_path path/to/model.pth --config_path path/to/config.json --out_path output/path/speech.wav
     ```
 
 - Run your own TTS and Vocoder models:
     ```
-    $ tts --text "Text for TTS" --model_path path/to/config.json --config_path path/to/model.pth.tar --out_path output/path/speech.wav
-        --vocoder_path path/to/vocoder.pth.tar --vocoder_config_path path/to/vocoder_config.json
+    $ tts --text "Text for TTS" --model_path path/to/config.json --config_path path/to/model.pth --out_path output/path/speech.wav
+        --vocoder_path path/to/vocoder.pth --vocoder_config_path path/to/vocoder_config.json
     ```
 
 ### Multi-speaker Models
@@ -86,7 +86,7 @@ def main():
 - Run your own multi-speaker TTS model:
 
     ```
-    $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/config.json --config_path path/to/model.pth.tar --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
+    $ tts --text "Text for TTS" --out_path output/path/speech.wav --model_path path/to/config.json --config_path path/to/model.pth --speakers_file_path path/to/speaker.json --speaker_idx <speaker_id>
     ```
     """
     # We remove Markdown code formatting programmatically here to allow us to copy-and-paste from main README to keep

TTS/bin/synthesize.py

@@ -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/README.md

@@ -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/generic_utils.py

@@ -5,7 +5,7 @@
 
 
 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)