Observations on the audio output
#1
by mobeidat - opened
Thanks for the excellent work on this. I tested and it works great, have the following observations:\
- I tested with a few examples that I have other models struggle with but it read them correctly some thing like 'الإعدادات', 'لهذا', etc...
- It does not speak digits correctly. I tried with Arabic numerals and Hindi numerals. Arabic numerals are spoken a bit better than Hindi but both are not understandable.
- It speaks too fast. I reduced cfg_weight to 0.1 but still faster than normal speech
thanks for the feedback, we work on second version of tther model where we are willing to solve these issues..
Omartificial-Intelligence-Space changed discussion status to closed