Merge pull request coqui-ai#3 from idiap/logging

Use Python logging instead of print()

TTS/api.py

@@ -1,3 +1,4 @@
+import logging
 import tempfile
 import warnings
 from pathlib import Path
@@ -9,6 +10,8 @@
 from TTS.utils.manage import ModelManager
 from TTS.utils.synthesizer import Synthesizer
 
+logger = logging.getLogger(__name__)
+
 
 class TTS(nn.Module):
     """TODO: Add voice conversion and Capacitron support."""
@@ -59,7 +62,7 @@ def __init__(
             gpu (bool, optional): Enable/disable GPU. Some models might be too slow on CPU. Defaults to False.
         """
         super().__init__()
-        self.manager = ModelManager(models_file=self.get_models_file_path(), progress_bar=progress_bar, verbose=False)
+        self.manager = ModelManager(models_file=self.get_models_file_path(), progress_bar=progress_bar)
         self.config = load_config(config_path) if config_path else None
         self.synthesizer = None
         self.voice_converter = None
@@ -122,7 +125,7 @@ def get_models_file_path():
 
     @staticmethod
     def list_models():
-        return ModelManager(models_file=TTS.get_models_file_path(), progress_bar=False, verbose=False).list_models()
+        return ModelManager(models_file=TTS.get_models_file_path(), progress_bar=False).list_models()
 
     def download_model_by_name(self, model_name: str):
         model_path, config_path, model_item = self.manager.download_model(model_name)

TTS/bin/compute_attention_masks.py

@@ -1,5 +1,6 @@
 import argparse
 import importlib
+import logging
 import os
 from argparse import RawTextHelpFormatter
 
@@ -13,9 +14,12 @@
 from TTS.tts.models import setup_model
 from TTS.tts.utils.text.characters import make_symbols, phonemes, symbols
 from TTS.utils.audio import AudioProcessor
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 from TTS.utils.io import load_checkpoint
 
 if __name__ == "__main__":
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     # pylint: disable=bad-option-value
     parser = argparse.ArgumentParser(
         description="""Extract attention masks from trained Tacotron/Tacotron2 models.

TTS/bin/compute_embeddings.py

@@ -1,4 +1,5 @@
 import argparse
+import logging
 import os
 from argparse import RawTextHelpFormatter
 
@@ -10,6 +11,7 @@
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.utils.managers import save_file
 from TTS.tts.utils.speakers import SpeakerManager
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
 def compute_embeddings(
@@ -100,6 +102,8 @@ def compute_embeddings(
 
 
 if __name__ == "__main__":
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     parser = argparse.ArgumentParser(
         description="""Compute embedding vectors for each audio file in a dataset and store them keyed by `{dataset_name}#{file_path}` in a .pth file\n\n"""
         """

TTS/bin/compute_statistics.py

@@ -3,6 +3,7 @@
 
 import argparse
 import glob
+import logging
 import os
 
 import numpy as np
@@ -12,10 +13,13 @@
 from TTS.config import load_config
 from TTS.tts.datasets import load_tts_samples
 from TTS.utils.audio import AudioProcessor
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
 def main():
     """Run preprocessing process."""
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     parser = argparse.ArgumentParser(description="Compute mean and variance of spectrogtram features.")
     parser.add_argument("config_path", type=str, help="TTS config file path to define audio processin parameters.")
     parser.add_argument("out_path", type=str, help="save path (directory and filename).")

TTS/bin/eval_encoder.py

@@ -1,4 +1,5 @@
 import argparse
+import logging
 from argparse import RawTextHelpFormatter
 
 import torch
@@ -7,6 +8,7 @@
 from TTS.config import load_config
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.utils.speakers import SpeakerManager
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
 def compute_encoder_accuracy(dataset_items, encoder_manager):
@@ -51,6 +53,8 @@ def compute_encoder_accuracy(dataset_items, encoder_manager):
 
 
 if __name__ == "__main__":
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     parser = argparse.ArgumentParser(
         description="""Compute the accuracy of the encoder.\n\n"""
         """

TTS/bin/extract_tts_spectrograms.py

@@ -2,6 +2,7 @@
 """Extract Mel spectrograms with teacher forcing."""
 
 import argparse
+import logging
 import os
 
 import numpy as np
@@ -17,11 +18,12 @@
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.utils.audio import AudioProcessor
 from TTS.utils.audio.numpy_transforms import quantize
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 use_cuda = torch.cuda.is_available()
 
 
-def setup_loader(ap, r, verbose=False):
+def setup_loader(ap, r):
     tokenizer, _ = TTSTokenizer.init_from_config(c)
     dataset = TTSDataset(
         outputs_per_step=r,
@@ -37,7 +39,6 @@ def setup_loader(ap, r, verbose=False):
         phoneme_cache_path=c.phoneme_cache_path,
         precompute_num_workers=0,
         use_noise_augment=False,
-        verbose=verbose,
         speaker_id_mapping=speaker_manager.name_to_id if c.use_speaker_embedding else None,
         d_vector_mapping=speaker_manager.embeddings if c.use_d_vector_file else None,
     )
@@ -257,7 +258,7 @@ def main(args):  # pylint: disable=redefined-outer-name
     print("\n > Model has {} parameters".format(num_params), flush=True)
     # set r
     r = 1 if c.model.lower() == "glow_tts" else model.decoder.r
-    own_loader = setup_loader(ap, r, verbose=True)
+    own_loader = setup_loader(ap, r)
 
     extract_spectrograms(
         own_loader,
@@ -272,6 +273,8 @@ def main(args):  # pylint: disable=redefined-outer-name
 
 
 if __name__ == "__main__":
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     parser = argparse.ArgumentParser()
     parser.add_argument("--config_path", type=str, help="Path to config file for training.", required=True)
     parser.add_argument("--checkpoint_path", type=str, help="Model file to be restored.", required=True)

TTS/bin/find_unique_chars.py

@@ -1,13 +1,17 @@
 """Find all the unique characters in a dataset"""
 
 import argparse
+import logging
 from argparse import RawTextHelpFormatter
 
 from TTS.config import load_config
 from TTS.tts.datasets import find_unique_chars, load_tts_samples
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
 def main():
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     # pylint: disable=bad-option-value
     parser = argparse.ArgumentParser(
         description="""Find all the unique characters or phonemes in a dataset.\n\n"""

TTS/bin/find_unique_phonemes.py

@@ -1,6 +1,7 @@
 """Find all the unique characters in a dataset"""
 
 import argparse
+import logging
 import multiprocessing
 from argparse import RawTextHelpFormatter
 
@@ -9,6 +10,7 @@
 from TTS.config import load_config
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.utils.text.phonemizers import Gruut
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
 def compute_phonemes(item):
@@ -18,6 +20,8 @@ def compute_phonemes(item):
 
 
 def main():
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     # pylint: disable=W0601
     global c, phonemizer
     # pylint: disable=bad-option-value

TTS/bin/remove_silence_using_vad.py

@@ -1,12 +1,14 @@
 import argparse
 import glob
+import logging
 import multiprocessing
 import os
 import pathlib
 
 import torch
 from tqdm import tqdm
 
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 from TTS.utils.vad import get_vad_model_and_utils, remove_silence
 
 torch.set_num_threads(1)
@@ -75,6 +77,8 @@ def preprocess_audios():
 
 
 if __name__ == "__main__":
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     parser = argparse.ArgumentParser(
         description="python TTS/bin/remove_silence_using_vad.py -i=VCTK-Corpus/ -o=VCTK-Corpus-removed-silence/ -g=wav48_silence_trimmed/*/*_mic1.flac --trim_just_beginning_and_end True"
     )

TTS/bin/synthesize.py

@@ -3,12 +3,17 @@
 
 import argparse
 import contextlib
+import logging
 import sys
 from argparse import RawTextHelpFormatter
 
 # pylint: disable=redefined-outer-name, unused-argument
 from pathlib import Path
 
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
+
+logger = logging.getLogger(__name__)
+
 description = """
 Synthesize speech on command line.
 
@@ -142,6 +147,8 @@ def str2bool(v):
 
 
 def main():
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     parser = argparse.ArgumentParser(
         description=description.replace("    ```\n", ""),
         formatter_class=RawTextHelpFormatter,
@@ -435,31 +442,37 @@ def main():
 
         # query speaker ids of a multi-speaker model.
         if args.list_speaker_idxs:
-            print(
-                " > Available speaker ids: (Set --speaker_idx flag to one of these values to use the multi-speaker model."
+            if synthesizer.tts_model.speaker_manager is None:
+                logger.info("Model only has a single speaker.")
+                return
+            logger.info(
+                "Available speaker ids: (Set --speaker_idx flag to one of these values to use the multi-speaker model."
             )
-            print(synthesizer.tts_model.speaker_manager.name_to_id)
+            logger.info(synthesizer.tts_model.speaker_manager.name_to_id)
             return
 
         # query langauge ids of a multi-lingual model.
         if args.list_language_idxs:
-            print(
-                " > Available language ids: (Set --language_idx flag to one of these values to use the multi-lingual model."
+            if synthesizer.tts_model.language_manager is None:
+                logger.info("Monolingual model.")
+                return
+            logger.info(
+                "Available language ids: (Set --language_idx flag to one of these values to use the multi-lingual model."
             )
-            print(synthesizer.tts_model.language_manager.name_to_id)
+            logger.info(synthesizer.tts_model.language_manager.name_to_id)
             return
 
         # check the arguments against a multi-speaker model.
         if synthesizer.tts_speakers_file and (not args.speaker_idx and not args.speaker_wav):
-            print(
-                " [!] Looks like you use a multi-speaker model. Define `--speaker_idx` to "
+            logger.error(
+                "Looks like you use a multi-speaker model. Define `--speaker_idx` to "
                 "select the target speaker. You can list the available speakers for this model by `--list_speaker_idxs`."
             )
             return
 
         # RUN THE SYNTHESIS
         if args.text:
-            print(" > Text: {}".format(args.text))
+            logger.info("Text: %s", args.text)
 
         # kick it
         if tts_path is not None:
@@ -484,8 +497,8 @@ def main():
             )
 
         # save the results
-        print(" > Saving output to {}".format(args.out_path))
         synthesizer.save_wav(wav, args.out_path, pipe_out=pipe_out)
+        logger.info("Saved output to %s", args.out_path)
 
 
 if __name__ == "__main__":

TTS/bin/train_encoder.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
+import logging
 import os
 import sys
 import time
@@ -19,6 +20,7 @@
 from TTS.encoder.utils.visual import plot_embeddings
 from TTS.tts.datasets import load_tts_samples
 from TTS.utils.audio import AudioProcessor
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 from TTS.utils.samplers import PerfectBatchSampler
 from TTS.utils.training import check_update
 
@@ -31,7 +33,7 @@
 print(" > Number of GPUs: ", num_gpus)
 
 
-def setup_loader(ap: AudioProcessor, is_val: bool = False, verbose: bool = False):
+def setup_loader(ap: AudioProcessor, is_val: bool = False):
     num_utter_per_class = c.num_utter_per_class if not is_val else c.eval_num_utter_per_class
     num_classes_in_batch = c.num_classes_in_batch if not is_val else c.eval_num_classes_in_batch
 
@@ -42,7 +44,6 @@ def setup_loader(ap: AudioProcessor, is_val: bool = False, verbose: bool = False
         voice_len=c.voice_len,
         num_utter_per_class=num_utter_per_class,
         num_classes_in_batch=num_classes_in_batch,
-        verbose=verbose,
         augmentation_config=c.audio_augmentation if not is_val else None,
         use_torch_spec=c.model_params.get("use_torch_spec", False),
     )
@@ -278,9 +279,9 @@ def main(args):  # pylint: disable=redefined-outer-name
     # pylint: disable=redefined-outer-name
     meta_data_train, meta_data_eval = load_tts_samples(c.datasets, eval_split=True)
 
-    train_data_loader, train_classes, map_classid_to_classname = setup_loader(ap, is_val=False, verbose=True)
+    train_data_loader, train_classes, map_classid_to_classname = setup_loader(ap, is_val=False)
     if c.run_eval:
-        eval_data_loader, _, _ = setup_loader(ap, is_val=True, verbose=True)
+        eval_data_loader, _, _ = setup_loader(ap, is_val=True)
     else:
         eval_data_loader = None
 
@@ -316,6 +317,8 @@ def main(args):  # pylint: disable=redefined-outer-name
 
 
 if __name__ == "__main__":
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     args, c, OUT_PATH, AUDIO_PATH, c_logger, dashboard_logger = init_training()
 
     try:

TTS/bin/train_tts.py

@@ -1,3 +1,4 @@
+import logging
 import os
 from dataclasses import dataclass, field
 
@@ -6,6 +7,7 @@
 from TTS.config import load_config, register_config
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models import setup_model
+from TTS.utils.generic_utils import ConsoleFormatter, setup_logger
 
 
 @dataclass
@@ -15,6 +17,8 @@ class TrainTTSArgs(TrainerArgs):
 
 def main():
     """Run `tts` model training directly by a `config.json` file."""
+    setup_logger("TTS", level=logging.INFO, screen=True, formatter=ConsoleFormatter())
+
     # init trainer args
     train_args = TrainTTSArgs()
     parser = train_args.init_argparse(arg_prefix="")