Merge pull request #22 from eginhard/unique-chars

refactor(bin.find_unique_chars): use existing function

.github/workflows/tests.yml

@@ -30,6 +30,7 @@ jobs:
       - name: Install Espeak
         if: contains(fromJSON('["inference_tests", "test_text", "test_tts", "test_tts2", "test_xtts", "test_zoo0", "test_zoo1", "test_zoo2"]'), matrix.subset)
         run: |
+          sudo apt-get update
           sudo apt-get install espeak espeak-ng
       - name: Install dependencies
         run: |

TTS/bin/find_unique_chars.py

@@ -4,7 +4,7 @@ import argparse
 from argparse import RawTextHelpFormatter
 
 from TTS.config import load_config
-from TTS.tts.datasets import load_tts_samples
+from TTS.tts.datasets import find_unique_chars, load_tts_samples
 
 
 def main():
@@ -29,17 +29,7 @@ def main():
     )
 
     items = train_items + eval_items
-
+    find_unique_chars(items)
-    texts = "".join(item["text"] for item in items)
-    chars = set(texts)
-    lower_chars = filter(lambda c: c.islower(), chars)
-    chars_force_lower = [c.lower() for c in chars]
-    chars_force_lower = set(chars_force_lower)
-
-    print(f" > Number of unique characters: {len(chars)}")
-    print(f" > Unique characters: {''.join(sorted(chars))}")
-    print(f" > Unique lower characters: {''.join(sorted(lower_chars))}")
-    print(f" > Unique all forced to lower characters: {''.join(sorted(chars_force_lower))}")
 
 
 if __name__ == "__main__":

TTS/tts/datasets/__init__.py

@@ -167,7 +167,7 @@ def _get_formatter_by_name(name):
 
 
 def find_unique_chars(data_samples, verbose=True):
-    texts = "".join(item[0] for item in data_samples)
+    texts = "".join(item["text"] for item in data_samples)
     chars = set(texts)
     lower_chars = filter(lambda c: c.islower(), chars)
     chars_force_lower = [c.lower() for c in chars]