I am also encountering an “Internal Server Error” while trying to use the Inference API for both my own fine-tuned Speech T5 model and the original Microsoft Speech T5 model. This issue persists across different environments, including Google Colab and Visual Studio Code.
I have opened a discussion on Hugging Face’s forum here: microsoft/speecht5_tts · Internal Server Error while using Inference API for Speech T5
If anyone has experienced similar issues or has a possible solution, please share!