The example doesn't work with the new model names

[rsxdalv]

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
diff_model,ts_model,vocoder,diffuser = load_models('Smolie-en',device)
print('Using:',device)

speaker_num = 0 # @param ["0", "1", "2", "3"] {type:"raw"}
text = "I freakin love how Elon came to life the moment they started talking about gaming and specifically diablo, you can tell that he didn't want that part of the discussion to end, while Lex to move on to the next subject! Once a true gamer, always a true gamer!" # @param {type:"string"}

ref_clips = glob.glob(speaker[speaker_num]+'*.wav')
audio,sr = infer_tts(text,ref_clips,diffuser,diff_model,ts_model,vocoder)

write('/content/test.wav',sr,audio)

---------------------------------------------------------------------------

AssertionError                            Traceback (most recent call last)
Cell In[6], [line 2](vscode-notebook-cell:?execution_count=6&line=2)
      [1](vscode-notebook-cell:?execution_count=6&line=1) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
----> [2](vscode-notebook-cell:?execution_count=6&line=2) diff_model,ts_model,vocoder,diffuser = load_models('Smolie-en',device)
      [3](vscode-notebook-cell:?execution_count=6&line=3) print('Using:',device)
      [5](vscode-notebook-cell:?execution_count=6&line=5) speaker_num = 0 # @param ["0", "1", "2", "3"] {type:"raw"}

File [c:\Users\admin\Desktop\one-click-installers-tts-main\installer_files\env\lib\site-packages\maha_tts\inference.py:92](/env/lib/site-packages/maha_tts/inference.py:92), in load_models(name, device)
     [74](/env/lib/site-packages/maha_tts/inference.py:74) def load_models(name,device=torch.device('cpu')):
     [75](/env/lib/site-packages/maha_tts/inference.py:75)     '''
     [76](/env/lib/site-packages/maha_tts/inference.py:76)     Load pre-trained models for different components of a text-to-speech system.
     [77](/env/lib/site-packages/maha_tts/inference.py:77) 
   (...)
     [89](/env/lib/site-packages/maha_tts/inference.py:89)     diffuser (object): Configured diffuser object for use in the diffusion model.
     [90](/env/lib/site-packages/maha_tts/inference.py:90)     '''
---> [92](/env/lib/site-packages/maha_tts/inference.py:92)     assert name in model_dirs, "no model name "+name
     [94](/env/lib/site-packages/maha_tts/inference.py:94)     checkpoint_diff = os.path.join(DEFAULT_MODELS_DIR,name,'s2a_latest.pt')
     [95](/env/lib/site-packages/maha_tts/inference.py:95)     checkpoint_ts = os.path.join(DEFAULT_MODELS_DIR,name,'t2s_best.pt')


AssertionError: no model name Smolie-en

if I try to use just "Smolie" it gets a 404 from huggingface, maybe something was renamed?

[rasenganai]

Hi, can you try reinstalling the repository, or maybe share some colab to reproduce this error.
The model is working fine in the repo main colab, please refer to it.

[rsxdalv]

Got it, thank you!
The pypi version is broken but if I install the repository then it works. Also the version counter is still 1.0.0 so I had to pip uninstall before I could do pip install .

[rasenganai]

Got it, I'll hide the pypi version for now.