Allow to train encoder

.gitignore

@@ -17,5 +17,7 @@
 *.sh
 synthesizer/saved_models/*
 vocoder/saved_models/*
+encoder/saved_models/*
 cp_hifigan/*
 !vocoder/saved_models/pretrained/*
+!encoder/saved_models/pretrained.pt

encoder/preprocess.py

@@ -117,6 +117,15 @@ def _preprocess_speaker_dirs(speaker_dirs, dataset_name, datasets_root, out_dir,
     logger.finalize()
     print("Done preprocessing %s.\n" % dataset_name)
 
+def preprocess_aidatatang_200zh(datasets_root: Path, out_dir: Path, skip_existing=False):
+    dataset_name = "aidatatang_200zh"
+    dataset_root, logger = _init_preprocess_dataset(dataset_name, datasets_root, out_dir)
+    if not dataset_root:
+        return 
+    # Preprocess all speakers
+    speaker_dirs = list(dataset_root.joinpath("corpus", "train").glob("*"))
+    _preprocess_speaker_dirs(speaker_dirs, dataset_name, datasets_root, out_dir, "wav",
+                                skip_existing, logger)
 
 def preprocess_librispeech(datasets_root: Path, out_dir: Path, skip_existing=False):
     for dataset_name in librispeech_datasets["train"]["other"]:

encoder_preprocess.py

@@ -1,4 +1,4 @@
-from encoder.preprocess import preprocess_librispeech, preprocess_voxceleb1, preprocess_voxceleb2
+from encoder.preprocess import preprocess_librispeech, preprocess_voxceleb1, preprocess_voxceleb2, preprocess_aidatatang_200zh
 from utils.argutils import print_args
 from pathlib import Path
 import argparse
@@ -10,17 +10,7 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser(
         description="Preprocesses audio files from datasets, encodes them as mel spectrograms and "
                     "writes them to the disk. This will allow you to train the encoder. The "
-                    "datasets required are at least one of VoxCeleb1, VoxCeleb2 and LibriSpeech. "
+                    "datasets required are at least one of LibriSpeech, VoxCeleb1, VoxCeleb2, aidatatang_200zh. ",
-                    "Ideally, you should have all three. You should extract them as they are "
-                    "after having downloaded them and put them in a same directory, e.g.:\n"
-                    "-[datasets_root]\n"
-                    "  -LibriSpeech\n"
-                    "    -train-other-500\n"
-                    "  -VoxCeleb1\n"
-                    "    -wav\n"
-                    "    -vox1_meta.csv\n"
-                    "  -VoxCeleb2\n"
-                    "    -dev",
         formatter_class=MyFormatter
     )
     parser.add_argument("datasets_root", type=Path, help=\
@@ -29,7 +19,7 @@ if __name__ == "__main__":
         "Path to the output directory that will contain the mel spectrograms. If left out, "
         "defaults to <datasets_root>/SV2TTS/encoder/")
     parser.add_argument("-d", "--datasets", type=str, 
-                        default="librispeech_other,voxceleb1,voxceleb2", help=\
+                        default="librispeech_other,voxceleb1,aidatatang_200zh", help=\
         "Comma-separated list of the name of the datasets you want to preprocess. Only the train "
         "set of these datasets will be used. Possible names: librispeech_other, voxceleb1, "
         "voxceleb2.")
@@ -63,6 +53,7 @@ if __name__ == "__main__":
         "librispeech_other": preprocess_librispeech,
         "voxceleb1": preprocess_voxceleb1,
         "voxceleb2": preprocess_voxceleb2,
+        "aidatatang_200zh": preprocess_aidatatang_200zh,
     }
     args = vars(args)
     for dataset in args.pop("datasets"):