Text-to-Speech
Safetensors
English
llama

What languages are support?

#2
by mzeid - opened

I have tried it with Arabic text, but I got this error:

RuntimeError Traceback (most recent call last)
in <cell line: 17>()
15 # Generate TTS output
16 # Without a speaker reference, the model generates speech with random speaker characteristics
---> 17 output = interface.generate(
18 text="أهلا وسهلا بكم جميعا ومرحباً",
19 temperature=0.1,

11 frames
/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight, bias)
368 self.groups,
369 )
--> 370 return F.conv1d(
371 input, weight, bias, self.stride, self.padding, self.dilation, self.groups
372 )

RuntimeError: Calculated padded input size per channel: (6). Kernel size: (7). Kernel size can't be greater than actual input size

Currently, only English is supported https://huggingface.co/OuteAI/OuteTTS-0.1-350M#model-details
Additionally, the current forced alignment implementation only supports the basic Latin alphabet (without capital letters).

Sign up or log in to comment