A GLaDOS TTS, using Forward Tacotron and HiFiGAN. Inference is fast and stable, even on the CPU. A low quality vocoder model is included for mobile use. Rudimentary TTS script included. Works perfectly on Linux, partially on Maybe someone smarter than me can make a GUI.
if i try to use the standalone glados.py, it works well
however if i try to use the engine, and call http://127.0.0.1:8124/synthesize/asdasd i will receive the following stack trace:
Forward Tacotron took 58.54463577270508ms
HiFiGAN took 426.1307716369629ms
[2024-06-28 00:42:09,879] ERROR in app: Exception on /synthesize/asdasd [GET]
Traceback (most recent call last):
File "C:\Users\Tancred\AppData\Local\Programs\Python\Python311\Lib\site-packages\flask\app.py", line 1473, in wsgi_app
response = self.full_dispatch_request()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Tancred\AppData\Local\Programs\Python\Python311\Lib\site-packages\flask\app.py", line 882, in full_dispatch_request
rv = self.handle_user_exception(e)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Tancred\AppData\Local\Programs\Python\Python311\Lib\site-packages\flask\app.py", line 880, in full_dispatch_request
rv = self.dispatch_request()
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Tancred\AppData\Local\Programs\Python\Python311\Lib\site-packages\flask\app.py", line 865, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args) # type: ignore[no-any-return]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Tancred\Downloads\glados-tts-main\glados-tts-main\engine.py", line 64, in synthesize
if(glados_tts(line, key)):
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Tancred\Downloads\glados-tts-main\glados-tts-main\engine.py", line 23, in glados_tts
glados.run_tts(text, alpha).export(output_file, format = "wav")
File "C:\Users\Tancred\AppData\Local\Programs\Python\Python311\Lib\site-packages\pydub\audio_segment.py", line 867, in export
out_f, _ = _fd_or_path_or_tempfile(out_f, 'wb+')
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Tancred\AppData\Local\Programs\Python\Python311\Lib\site-packages\pydub\utils.py", line 60, in _fd_or_path_or_tempfile
fd = open(fd, mode=mode)
^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: 'audio/GLaDOS-tts-temp-output-129.1948433.wav'
what am i doing wrong or is something broken?
thank you :)
if i try to use the standalone
glados.py, it works well however if i try to use the engine, and callhttp://127.0.0.1:8124/synthesize/asdasdi will receive the following stack trace:what am i doing wrong or is something broken? thank you :)