From 0fb4cb2dc8f06f63e7e522f247b37b82201c7a63 Mon Sep 17 00:00:00 2001
From: Tasha Upchurch <TashaSkyUp@gmail.com>
Date: Sun, 19 May 2024 11:40:09 -0400
Subject: [PATCH] Updated xttscli.py script to handle multiple texts, absolute
 folder paths, and file input for text generation.

---
 modules/xttscli.py | 51 +++++++++++++++++++++++++++++-----------------
 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/modules/xttscli.py b/modules/xttscli.py
index 062a974..dae6525 100644
--- a/modules/xttscli.py
+++ b/modules/xttscli.py
@@ -3,6 +3,7 @@ import torch.multiprocessing as mp
 
 from concurrent.futures import ProcessPoolExecutor, as_completed
 
+
 def generate_xtts_for_text(text, file, lang, speaker):
     from TTS.api import TTS
     import torch
@@ -20,29 +21,37 @@ def generate_xtts(**kwargs):
     import torch
     import ast
     import uuid
+    import os
     from concurrent.futures import ProcessPoolExecutor, as_completed
 
     torch.cuda.empty_cache()
 
     text = kwargs.get('text')
     folder = kwargs.get('folder', '.')
+    # make the folder absolute
+    folder = os.path.abspath(folder)
     lang = kwargs.get('lang', 'en')
     speaker = kwargs.get('speaker', '')
 
-    try:
-        texts = ast.literal_eval(text)
-    except SyntaxError:
-        texts = [text]
+    if isinstance(text, str):
+        if text != None and text.startswith("[") and text.endswith("]"):
+            try:
+                texts = ast.literal_eval(text)
+            except SyntaxError:
+                texts = [text]
+    elif isinstance(text, list):
+        texts = text
 
     o_files = []
-    batch_size = 3
+    batch_size = 2
     with ProcessPoolExecutor(max_workers=batch_size) as executor:
         futures = []
         for i, text in enumerate(texts):
-            ii = str(i).zfill(1 + len(str(1 + len(texts))))
-            file_to_use = f"{folder}/tts_{ii}_{str(uuid.uuid4())}.wav"
-            future = executor.submit(generate_xtts_for_text, text, file_to_use, lang, speaker)
-            futures.append((future, file_to_use))
+            if len(text)>1:
+                ii = str(i).zfill(1 + len(str(1 + len(texts))))
+                file_to_use = f"{folder}/tts_{ii}_{str(uuid.uuid4())}.wav"
+                future = executor.submit(generate_xtts_for_text, text, file_to_use, lang, speaker)
+                futures.append((future, file_to_use))
 
         for future, file_to_use in futures:
             future.result()
@@ -53,8 +62,6 @@ def generate_xtts(**kwargs):
     return (o_files[0], o_files,)
 
 
-
-
 # def generate_xtts_for_text_advanced(text, file, lang, speaker):
 #     from TTS.api import TTS
 #     import torch
@@ -70,25 +77,31 @@ def generate_xtts(**kwargs):
 #     something = manager.
 
 
-
-
-
-
-
-
 def main():
+    import os
     parser = argparse.ArgumentParser(description='Generate  from given text.')
     parser.add_argument('--text', help='Text to generate  for')
     parser.add_argument('--folder', type=str, default='.', help='output folder')
     parser.add_argument('--lang', type=str, default='en')
     parser.add_argument('--speaker', type=str, default='', help='Speaker wav use for generation')
+    parser.add_argument('--file', type=str, default="", help='newline seperated file.')
 
     args = parser.parse_args()
     kwargs = vars(args)
 
-    print(f"Generating with the following arguments: {kwargs}")
+    # test if file is set if it is open it
+    if kwargs['file'] is not None:
+        with open(kwargs['file']) as f:
+            kwargs['text'] = f.read().split('\n')
+
+    # make sure the speaker file exists
+    if kwargs['speaker'] is not None:
+        if not os.path.exists(kwargs['speaker']):
+            raise ValueError(f"Speaker file {kwargs['speaker']} does not exist.")
+
     generated_files = generate_xtts(**kwargs)
     print(f"Generated files: {generated_files}")
 
+
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()