I used the F5 TTS tool on Hugging Face and I generated 15 minutes of normal speech and trained it on Google Colab for 250 epochs.

Tip: Lower the transpose number into the minus numbers for better accurate results with this voice model, as I tried it at the default number of 0 and it sounded a bit high and slightly off and when I lowered the transpose number it sounded better and accurate.

Additional Details:

Tags: Frito-Lay, huggingface, ai-model

Related URL: https://huggingface.co/Ryanham1lton/ChesterCheetahJM/resolve/main/Chester%20Cheetah.zip?download=true

Download Link: https://huggingface.co/Ryanham1lton/ChesterCheetahJM/resolve/main/Chester%20Cheetah.zip?download=true Hosted on Hugging Face