common voice preprocessor and tests, small refactoring within tests

datasets/preprocess.py

@@ -1,6 +1,7 @@
 import os
 import random
 
+
 def tts_cache(root_path, meta_file):
     """This format is set for the meta-file generated by extract_features.py"""
     txt_file = os.path.join(root_path, meta_file)
@@ -109,7 +110,23 @@ def nancy(root_path, meta_file):
         for line in ttf:
             id = line.split()[1]
             text = line[line.find('"')+1:line.rfind('"')-1]
-            wav_file = root_path + 'wavn/' + id + '.wav'
+            wav_file = os.path.join(root_path, "wavn", id + ".wav")
             items.append([text, wav_file])
     random.shuffle(items)    
-    return items
+    return items
+
+
+def common_voice(root_path, meta_file):
+    """Normalize the common voice meta data file to TTS format."""
+    txt_file = os.path.join(root_path, meta_file)
+    items = []
+    with open(txt_file, 'r') as ttf:
+        for line in ttf:
+            if line.startswith("client_id"):
+                continue
+            cols = line.split("\t")
+            text = cols[2]
+            # Files need to be first converted to wav...
+            wav_file = os.path.join(root_path, "clips", cols[1] + ".wav")
+            items.append([text, wav_file])
+    return items