:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
I was wondering how the size of the character set in the processor impacts the learning of the model. Would for example have a processor being able to handle most western European languages - so with all normal alphabet chars as well as special chars in each language - train slower ?
This would include all the accented character, in French, German, Czech, Slovak, as well as From countries from Northern Europe.
The char list would get pretty long and I'm afraid it's going to slow training.
Has anybody trained with a recognisably long char set or know more details about how it would affect the model ?
Hi,
I was wondering how the size of the character set in the processor impacts the learning of the model. Would for example have a processor being able to handle most western European languages - so with all normal alphabet chars as well as special chars in each language - train slower ?
This would include all the accented character, in French, German, Czech, Slovak, as well as From countries from Northern Europe. The char list would get pretty long and I'm afraid it's going to slow training.
Has anybody trained with a recognisably long char set or know more details about how it would affect the model ?
Thanks