Text-to-Speech
GGUF
English
Inference Endpoints

error load model

#3
by NickyNicky - opened

!pip install outetts
!pip install llama-cpp-python
!sudo apt-get install libportaudio2
!sudo apt-get install libasound-dev

making attention of type 'vanilla' with 768 in_channels

Exception Traceback (most recent call last)
in <cell line: 7>()
5
6 # Or initialize the interface with a GGUF model
----> 7 interface = InterfaceGGUF("OuteAI/OuteTTS-0.1-350M-GGUF")
8
9 # Generate TTS output

5 frames
/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_fast.py in init(self, *args, **kwargs)
113 elif fast_tokenizer_file is not None and not from_slow:
114 # We have a serialization from tokenizers which let us directly build the backend
--> 115 fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
116 elif slow_tokenizer is not None:
117 # We need to convert a slow tokenizer to build the backend

Exception: data did not match any variant of untagged enum ModelWrapper at line 352271 column 3

https://colab.research.google.com/drive/1mYZZYKQmopg7XOTUtWFa5ctMgEsOu4OZ#scrollTo=MrXoENyr3u8-

same issue here as well

I've addressed this issue and provided a solution. Please refer to the discussion here https://huggingface.co/OuteAI/OuteTTS-0.1-350M/discussions/1#6729e14f88ec3429d0e8233d

Sign up or log in to comment