The onlyspeaktts from pandaily591

pandaily591 / onlyspeaktts Goto Github PK

View Code? Open in Web Editor NEW

Made slight modifications to the Tortoise API, provided 3 additional scripts to make using Tortoise easier. Less focus on cloning makes speech generation much faster by default.

License: Apache License 2.0

Python 76.04% Jupyter Notebook 1.69% HTML 22.27%

onlyspeaktts's People

Contributors

Stargazers

Watchers

onlyspeaktts's Issues

Where to get the .pt files?

Where can I find the .pt files that should be in the same folder as the voices? It is erroring for me trying to load the .pt files:

 * Serving Flask app 'server'
 * Debug mode: off
CHANGING VOICE...
Loaded 1.mp3
Loaded 2.mp3
Loaded 3.mp3
Loaded 4.mp3
Loaded 5.mp3
[2023-10-21 12:34:38,907] ERROR in app: Exception on / [POST]
Traceback (most recent call last):
  File "C:\Users\root\anaconda3\envs\OnlySpeakTTS\lib\site-packages\flask\app.py", line 1455, in wsgi_app
    response = self.full_dispatch_request()
  File "C:\Users\root\anaconda3\envs\OnlySpeakTTS\lib\site-packages\flask\app.py", line 869, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "C:\Users\root\anaconda3\envs\OnlySpeakTTS\lib\site-packages\flask\app.py", line 867, in full_dispatch_request
    rv = self.dispatch_request()
  File "C:\Users\root\anaconda3\envs\OnlySpeakTTS\lib\site-packages\flask\app.py", line 852, in dispatch_request
    return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
  File "C:\ai\OnlySpeakTTS\server.py", line 55, in result
    LOADED_VOICE = synthesizer.load_voice(os.path.join("voice_tensors", CURRENT_VOICE))
  File "C:\ai\OnlySpeakTTS\src\speech.py", line 151, in load_voice
    voice.append(torch.load(f"{voice_path}/Auto_Conditioning.pt"))
  File "C:\Users\root\anaconda3\envs\OnlySpeakTTS\lib\site-packages\torch\serialization.py", line 986, in load
    with _open_file_like(f, 'rb') as opened_file:
  File "C:\Users\root\anaconda3\envs\OnlySpeakTTS\lib\site-packages\torch\serialization.py", line 435, in _open_file_like
    return _open_file(name_or_buffer, mode)
  File "C:\Users\root\anaconda3\envs\OnlySpeakTTS\lib\site-packages\torch\serialization.py", line 416, in __init__
    super().__init__(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'voice_tensors\\natlamir/Auto_Conditioning.pt'

Recommend Projects