0.17.1

Author: matatonic

README.md

@@ -30,6 +30,11 @@ If you find a better voice match for `tts-1` or `tts-1-hd`, please let me know s
 
 ## Recent Changes
 
+Version 0.17.1, 2024-07-01
+
+* fix ROCm (add langdetect to requirements-rocm.txt)
+* Fix zh-cn for xtts
+
 Version 0.17.0, 2024-07-01
 
 * Automatic language detection, thanks [@RodolfoCastanheira](https://github.com/RodolfoCastanheira)

add_voice.py

@@ -11,8 +11,8 @@
 
 parser.add_argument('sample', action='store', help="Set the wav sample file")
 parser.add_argument('-n', '--name', action='store', help="Set the name for the voice (by default will use the WAV file name)")
-parser.add_argument('-l', '--language', action='store', default="en", help="Set the language for the voice",
-                    choices=['en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr', 'ru', 'nl', 'cs', 'ar', 'zh-cn', 'ja', 'hu', 'ko'])
+parser.add_argument('-l', '--language', action='store', default="auto", help="Set the language for the voice",
+                    choices=['auto', 'en', 'es', 'fr', 'de', 'it', 'pt', 'pl', 'tr', 'ru', 'nl', 'cs', 'ar', 'zh-cn', 'ja', 'hu', 'ko', 'hi'])
 parser.add_argument('--openai-model', action='store', default="tts-1-hd", help="Set the openai model for the voice")
 parser.add_argument('--xtts-model', action='store', default="xtts", help="Set the xtts model for the voice (if using a custom model, also set model_path)")
 parser.add_argument('--model-path', action='store', default=None, help="Set the path for a custom xtts model")

requirements-rocm.txt

@@ -3,6 +3,7 @@ uvicorn
 loguru
 piper-tts
 coqui-tts
+langdetect
 # Creating an environment where deepspeed works is complex, for now it will be disabled by default.
 #deepspeed
 torch; --index-url https://download.pytorch.org/whl/rocm5.7; sys_platform == "linux"

speech.py

@@ -296,7 +296,11 @@ async def generate_speech(request: GenerateSpeechRequest):
         hf_generate_kwargs['enable_text_splitting'] = hf_generate_kwargs.get('enable_text_splitting', True) # change the default to true
 
         if hf_generate_kwargs['enable_text_splitting']:
-            all_text = split_sentence(input_text, language, xtts.xtts.tokenizer.char_limits[language])
+            if language == 'zh-cn':
+                split_lang = 'zh'
+            else:
+                split_lang = language
+            all_text = split_sentence(input_text, split_lang, xtts.xtts.tokenizer.char_limits[split_lang])
         else:
             all_text = [input_text]
 

voice_to_speaker.default.yaml

@@ -46,8 +46,9 @@ tts-1-hd:
     model: xtts
     speaker: voices/shimmer.wav
   me:
-    model: xtts_v2.0.2 # you can specify different xtts version
+    model: xtts_v2.0.2 # you can specify an older xtts version
     speaker: voices/me.wav # this could be you
+    language: auto
     enable_text_splitting: True
     length_penalty: 1.0
     repetition_penalty: 10