Update model file extension (#1422)

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

* Update docs

* Rename more

* Find model files

.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
+    $ 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.tar --vocoder_config_path path/to/vocoder_config.json
+        --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 @@ These masks can be used for different purposes including training a TTS model wi
         """
 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 @@ parser = argparse.ArgumentParser(
     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

@@ -1,55 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-
-import os
-import pathlib
-import subprocess
-import time
-
-import torch
-from trainer import TrainerArgs
-
-
-def main():
-    """
-    Call train.py as a new process and pass command arguments
-    """
-    parser = TrainerArgs().init_argparse(arg_prefix="")
-    parser.add_argument("--script", type=str, help="Target training script to distibute.")
-    args, unargs = parser.parse_known_args()
-
-    num_gpus = torch.cuda.device_count()
-    group_id = time.strftime("%Y_%m_%d-%H%M%S")
-
-    # set arguments for train.py
-    folder_path = pathlib.Path(__file__).parent.absolute()
-    if os.path.exists(os.path.join(folder_path, args.script)):
-        command = [os.path.join(folder_path, args.script)]
-    else:
-        command = [args.script]
-    command.append("--continue_path={}".format(args.continue_path))
-    command.append("--restore_path={}".format(args.restore_path))
-    command.append("--config_path={}".format(args.config_path))
-    command.append("--group_id=group_{}".format(group_id))
-    command.append("--use_ddp=true")
-    command += unargs
-    command.append("")
-
-    # run a processes per GPU
-    processes = []
-    for i in range(num_gpus):
-        my_env = os.environ.copy()
-        my_env["PYTHON_EGG_CACHE"] = "/tmp/tmp{}".format(i)
-        command[-1] = "--rank={}".format(i)
-        # prevent stdout for processes with rank != 0
-        stdout = None
-        p = subprocess.Popen(["python3"] + command, stdout=stdout, env=my_env)  # pylint: disable=consider-using-with
-        processes.append(p)
-        print(command)
-
-    for p in processes:
-        p.wait()
-
-
-if __name__ == "__main__":
-    main()

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/bin/synthesize.py

@@ -60,13 +60,13 @@ If you don't specify any models, then it uses LJSpeech based English model.
 - 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
+    $ 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.tar --vocoder_config_path path/to/vocoder_config.json
+        --vocoder_path path/to/vocoder.pth --vocoder_config_path path/to/vocoder_config.json
     ```
 
 ### Multi-speaker Models
@@ -86,7 +86,7 @@ If you don't specify any models, then it uses LJSpeech based English model.
 - 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/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/server/README.md

@@ -21,4 +21,4 @@ Run the server with the official models on a GPU.
 ```CUDA_VISIBLE_DEVICES="0" python TTS/server/server.py  --model_name tts_models/en/ljspeech/tacotron2-DCA --vocoder_name vocoder_models/en/ljspeech/multiband-melgan --use_cuda True```
 
 Run the server with a custom models.
-```python TTS/server/server.py  --tts_checkpoint /path/to/tts/model.pth.tar --tts_config /path/to/tts/config.json --vocoder_checkpoint /path/to/vocoder/model.pth.tar --vocoder_config /path/to/vocoder/config.json```
+```python TTS/server/server.py  --tts_checkpoint /path/to/tts/model.pth --tts_config /path/to/tts/config.json --vocoder_checkpoint /path/to/vocoder/model.pth --vocoder_config /path/to/vocoder/config.json```

TTS/server/conf.json

@@ -1,6 +1,6 @@
 {
     "tts_path":"/media/erogol/data_ssd/Models/libri_tts/5049/",  // tts model root folder
-    "tts_file":"best_model.pth.tar",     // tts checkpoint file
+    "tts_file":"best_model.pth",     // tts checkpoint file
     "tts_config":"config.json",     // tts config.json file
     "tts_speakers": null,           // json file listing speaker ids. null if no speaker embedding.
     "vocoder_config":null,

TTS/utils/audio.py

@@ -371,7 +371,7 @@ class AudioProcessor(object):
             self.hop_length = hop_length
             self.win_length = win_length
         assert min_level_db != 0.0, " [!] min_level_db is 0"
-        assert self.win_length <= self.fft_size, " [!] win_length cannot be larger than fft_size"
+        assert self.win_length <= self.fft_size, f" [!] win_length cannot be larger than fft_size - {self.win_length} vs {self.fft_size}"
         members = vars(self)
         if verbose:
             print(" > Setting up Audio Processor...")

TTS/utils/generic_utils.py

@@ -67,7 +67,7 @@ def get_experiment_folder_path(root_path, model_name):
 def remove_experiment_folder(experiment_path):
     """Check folder if there is a checkpoint, otherwise remove the folder"""
     fs = fsspec.get_mapper(experiment_path).fs
-    checkpoint_files = fs.glob(experiment_path + "/*.pth.tar")
+    checkpoint_files = fs.glob(experiment_path + "/*.pth")
     if not checkpoint_files:
         if fs.exists(experiment_path):
             fs.rm(experiment_path, recursive=True)

TTS/utils/io.py

@@ -140,7 +140,7 @@ def save_checkpoint(
     output_folder,
     **kwargs,
 ):
-    file_name = "checkpoint_{}.pth.tar".format(current_step)
+    file_name = "checkpoint_{}.pth".format(current_step)
     checkpoint_path = os.path.join(output_folder, file_name)
     print("\n > CHECKPOINT : {}".format(checkpoint_path))
     save_model(
@@ -170,7 +170,7 @@ def save_best_model(
     **kwargs,
 ):
     if current_loss < best_loss:
-        best_model_name = f"best_model_{current_step}.pth.tar"
+        best_model_name = f"best_model_{current_step}.pth"
         checkpoint_path = os.path.join(out_path, best_model_name)
         print(" > BEST MODEL : {}".format(checkpoint_path))
         save_model(
@@ -187,12 +187,12 @@ def save_best_model(
         fs = fsspec.get_mapper(out_path).fs
         # only delete previous if current is saved successfully
         if not keep_all_best or (current_step < keep_after):
-            model_names = fs.glob(os.path.join(out_path, "best_model*.pth.tar"))
+            model_names = fs.glob(os.path.join(out_path, "best_model*.pth"))
             for model_name in model_names:
                 if os.path.basename(model_name) != best_model_name:
                     fs.rm(model_name)
         # create a shortcut which always points to the currently best model
-        shortcut_name = "best_model.pth.tar"
+        shortcut_name = "best_model.pth"
         shortcut_path = os.path.join(out_path, shortcut_name)
         fs.copy(checkpoint_path, shortcut_path)
         best_loss = current_loss

TTS/utils/manage.py

@@ -3,6 +3,7 @@ import json
 import os
 import zipfile
 from pathlib import Path
+from typing import Tuple
 from shutil import copyfile, rmtree
 
 import requests
@@ -114,7 +115,7 @@ 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 +128,7 @@ 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):
@@ -139,8 +140,32 @@ class ModelManager(object):
             self._download_zip_file(model_item["github_rls_url"], output_path)
         # update paths in the config.json
         self._update_paths(output_path, output_config_path)
+        # find downloaded files
+        output_model_path, output_config_path = self._find_files(output_path)
         return output_model_path, output_config_path, model_item
 
+    def _find_files(self, output_path:str) -> Tuple[str, str]:
+        """Find the model and config files in the output path
+
+        Args:
+            output_path (str): path to the model files
+
+        Returns:
+            Tuple[str, str]: path to the model file and config file
+        """
+        model_file = None
+        config_file = None
+        for file_name in os.listdir(output_path):
+            if file_name in ["model_file.pth", "model_file.pth.tar", "model.pth"]:
+                model_file = os.path.join(output_path, file_name)
+            elif file_name == "config.json":
+                config_file = os.path.join(output_path, file_name)
+        if model_file is None:
+            raise ValueError(" [!] Model file not found in the output path")
+        if config_file is None:
+            raise ValueError(" [!] Config file not found in the output path")
+        return model_file, config_file
+
     def _update_paths(self, output_path: str, config_path: str) -> None:
         """Update paths for certain files in config.json after download.
 
@@ -152,7 +177,7 @@ 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)

TTS/vocoder/README.md

@@ -29,7 +29,7 @@ You can continue a previous training run by the following command.
 
 You can fine-tune a pre-trained model by the following command.
 
-```CUDA_VISIBLE_DEVICES='0' python tts/bin/train_vocoder.py --restore_path path/to/your/model.pth.tar```
+```CUDA_VISIBLE_DEVICES='0' python tts/bin/train_vocoder.py --restore_path path/to/your/model.pth```
 
 Restoring a model starts a new training in a different folder. It only restores model weights with the given checkpoint file. However, continuing a training starts from the same directory where the previous training run left off.
 

docs/source/finetuning.md

@@ -93,13 +93,13 @@ them and fine-tune it for your own dataset. This will help you in two main ways:
 
     ```bash
     CUDA_VISIBLE_DEVICES="0" python recipes/ljspeech/glow_tts/train_glowtts.py \
-        --restore_path  /home/ubuntu/.local/share/tts/tts_models--en--ljspeech--glow-tts/model_file.pth.tar
+        --restore_path  /home/ubuntu/.local/share/tts/tts_models--en--ljspeech--glow-tts/model_file.pth
     ```
 
     ```bash
     CUDA_VISIBLE_DEVICES="0" python TTS/bin/train_tts.py \
         --config_path  /home/ubuntu/.local/share/tts/tts_models--en--ljspeech--glow-tts/config.json \
-        --restore_path  /home/ubuntu/.local/share/tts/tts_models--en--ljspeech--glow-tts/model_file.pth.tar
+        --restore_path  /home/ubuntu/.local/share/tts/tts_models--en--ljspeech--glow-tts/model_file.pth
     ```
 
     As stated above, you can also use command-line arguments to change the model configuration.
@@ -107,7 +107,7 @@ them and fine-tune it for your own dataset. This will help you in two main ways:
 
     ```bash
     CUDA_VISIBLE_DEVICES="0" python recipes/ljspeech/glow_tts/train_glowtts.py \
-        --restore_path  /home/ubuntu/.local/share/tts/tts_models--en--ljspeech--glow-tts/model_file.pth.tar
+        --restore_path  /home/ubuntu/.local/share/tts/tts_models--en--ljspeech--glow-tts/model_file.pth
         --coqpit.run_name "glow-tts-finetune" \
         --coqpit.lr 0.00001
     ```

docs/source/inference.md

@@ -44,7 +44,7 @@ Run your own TTS model (Using Griffin-Lim Vocoder)
 
 ```bash
 tts --text "Text for TTS" \
-    --model_path path/to/model.pth.tar \
+    --model_path path/to/model.pth \
     --config_path path/to/config.json \
     --out_path folder/to/save/output.wav
 ```
@@ -54,9 +54,9 @@ Run your own TTS and Vocoder models
 ```bash
 tts --text "Text for TTS" \
     --config_path path/to/config.json \
-    --model_path path/to/model.pth.tar \
+    --model_path path/to/model.pth \
     --out_path folder/to/save/output.wav \
-    --vocoder_path path/to/vocoder.pth.tar \
+    --vocoder_path path/to/vocoder.pth \
     --vocoder_config_path path/to/vocoder_config.json
 ```
 

docs/source/training_a_model.md

@@ -33,7 +33,7 @@
     If you like to run a multi-gpu training using DDP back-end,
 
     ```bash
-    $ CUDA_VISIBLE_DEVICES="0, 1, 2" python TTS/bin/distribute.py --script <path_to_your_script>/train_glowtts.py
+    $ CUDA_VISIBLE_DEVICES="0, 1, 2" python -m trainer.distribute --script <path_to_your_script>/train_glowtts.py
     ```
 
     The example above runs a multi-gpu training using GPUs `0, 1, 2`.
@@ -122,7 +122,7 @@
 
     ```bash
     $ tts --text "Text for TTS" \
-          --model_path path/to/checkpoint_x.pth.tar \
+          --model_path path/to/checkpoint_x.pth \
           --config_path path/to/config.json \
           --out_path folder/to/save/output.wav
     ```

docs/source/tutorial_for_nervous_beginners.md

@@ -50,13 +50,13 @@ A breakdown of a simple script that trains a GlowTTS model on the LJspeech datas
     - Fine-tune a model.
 
         ```bash
-        CUDA_VISIBLE_DEVICES=0 python train.py --restore_path path/to/model/checkpoint.pth.tar
+        CUDA_VISIBLE_DEVICES=0 python train.py --restore_path path/to/model/checkpoint.pth
         ```
 
     - Run multi-gpu training.
 
         ```bash
-        CUDA_VISIBLE_DEVICES=0,1,2 python TTS/bin/distribute.py --script train.py
+        CUDA_VISIBLE_DEVICES=0,1,2 python -m trainer.distribute --script train.py
         ```
 
 ### CLI Way

notebooks/ExtractTTSpectrogram.ipynb

@@ -66,7 +66,7 @@
     "DATASET = \"ljspeech\"\n",
     "METADATA_FILE = \"metadata.csv\"\n",
     "CONFIG_PATH = \"/home/ubuntu/.local/share/tts/tts_models--en--ljspeech--tacotron2-DDC_ph/config.json\"\n",
-    "MODEL_FILE = \"/home/ubuntu/.local/share/tts/tts_models--en--ljspeech--tacotron2-DDC_ph/model_file.pth.tar\"\n",
+    "MODEL_FILE = \"/home/ubuntu/.local/share/tts/tts_models--en--ljspeech--tacotron2-DDC_ph/model_file.pth\"\n",
     "BATCH_SIZE = 32\n",
     "\n",
     "QUANTIZED_WAV = False\n",

notebooks/PlotUmapLibriTTS.ipynb

@@ -66,7 +66,7 @@
    "outputs": [],
    "source": [
     "MODEL_RUN_PATH = \"/media/erogol/data_ssd/Models/libri_tts/speaker_encoder/libritts_360-half-October-31-2019_04+54PM-19d2f5f/\"\n",
-    "MODEL_PATH = MODEL_RUN_PATH + \"best_model.pth.tar\"\n",
+    "MODEL_PATH = MODEL_RUN_PATH + \"best_model.pth\"\n",
     "CONFIG_PATH = MODEL_RUN_PATH + \"config.json\"\n",
     "\n",
     "# My single speaker locations\n",

notebooks/TestAttention.ipynb

@@ -73,7 +73,7 @@
     "\n",
     "# Set constants\n",
     "ROOT_PATH = '/home/erogol/Models/LJSpeech/ljspeech-May-20-2020_12+29PM-1835628/'\n",
-    "MODEL_PATH = ROOT_PATH + '/best_model.pth.tar'\n",
+    "MODEL_PATH = ROOT_PATH + '/best_model.pth'\n",
     "CONFIG_PATH = ROOT_PATH + '/config.json'\n",
     "OUT_FOLDER = './hard_sentences/'\n",
     "CONFIG = load_config(CONFIG_PATH)\n",

notebooks/dataset_analysis/AnalyzeDataset.ipynb

@@ -416,7 +416,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.9.5"
   }
  },
  "nbformat": 4,

tests/aux_tests/test_extract_tts_spectrograms.py

@@ -15,7 +15,7 @@ class TestExtractTTSSpectrograms(unittest.TestCase):
     def test_GlowTTS():
         # set paths
         config_path = os.path.join(get_tests_input_path(), "test_glow_tts.json")
-        checkpoint_path = os.path.join(get_tests_output_path(), "checkpoint_test.pth.tar")
+        checkpoint_path = os.path.join(get_tests_output_path(), "checkpoint_test.pth")
         output_path = os.path.join(get_tests_output_path(), "output_extract_tts_spectrograms/")
         # load config
         c = load_config(config_path)
@@ -33,7 +33,7 @@ class TestExtractTTSSpectrograms(unittest.TestCase):
     def test_Tacotron2():
         # set paths
         config_path = os.path.join(get_tests_input_path(), "test_tacotron2_config.json")
-        checkpoint_path = os.path.join(get_tests_output_path(), "checkpoint_test.pth.tar")
+        checkpoint_path = os.path.join(get_tests_output_path(), "checkpoint_test.pth")
         output_path = os.path.join(get_tests_output_path(), "output_extract_tts_spectrograms/")
         # load config
         c = load_config(config_path)
@@ -51,7 +51,7 @@ class TestExtractTTSSpectrograms(unittest.TestCase):
     def test_Tacotron():
         # set paths
         config_path = os.path.join(get_tests_input_path(), "test_tacotron_config.json")
-        checkpoint_path = os.path.join(get_tests_output_path(), "checkpoint_test.pth.tar")
+        checkpoint_path = os.path.join(get_tests_output_path(), "checkpoint_test.pth")
         output_path = os.path.join(get_tests_output_path(), "output_extract_tts_spectrograms/")
         # load config
         c = load_config(config_path)

tests/aux_tests/test_speaker_manager.py

@@ -12,7 +12,7 @@ from TTS.tts.utils.speakers import SpeakerManager
 from TTS.utils.audio import AudioProcessor
 
 encoder_config_path = os.path.join(get_tests_input_path(), "test_speaker_encoder_config.json")
-encoder_model_path = os.path.join(get_tests_input_path(), "checkpoint_0.pth.tar")
+encoder_model_path = os.path.join(get_tests_input_path(), "checkpoint_0.pth")
 sample_wav_path = os.path.join(get_tests_input_path(), "../data/ljspeech/wavs/LJ001-0001.wav")
 sample_wav_path2 = os.path.join(get_tests_input_path(), "../data/ljspeech/wavs/LJ001-0002.wav")
 d_vectors_file_path = os.path.join(get_tests_input_path(), "../data/dummy_speakers.json")

tests/inference_tests/test_synthesizer.py

@@ -20,7 +20,7 @@ class SynthesizerTest(unittest.TestCase):
     def test_in_out(self):
         self._create_random_model()
         tts_root_path = get_tests_output_path()
-        tts_checkpoint = os.path.join(tts_root_path, "checkpoint_10.pth.tar")
+        tts_checkpoint = os.path.join(tts_root_path, "checkpoint_10.pth")
         tts_config = os.path.join(tts_root_path, "dummy_model_config.json")
         synthesizer = Synthesizer(tts_checkpoint, tts_config, None, None)
         synthesizer.tts("Better this test works!!")

tests/inputs/server_config.json

@@ -1,5 +1,5 @@
 {
-    "tts_checkpoint":"checkpoint_10.pth.tar",     // tts checkpoint file
+    "tts_checkpoint":"checkpoint_10.pth",     // tts checkpoint file
     "tts_config":"dummy_model_config.json",     // tts config.json file
     "tts_speakers": null,           // json file listing speaker ids. null if no speaker embedding.
     "wavernn_lib_path": null,   // Rootpath to wavernn project folder to be imported. If this is null, model uses GL for speech synthesis.