I am planning to test to do a Swedish TTS from scratch with a custom voice.
If you have any input on the process please let me know
- I am building a swedish large dataset with transcriptions. The set however has several different speakers.
- I plan to train a model from scratch using this set
- Once trained, i plan to use the SMALLER custom voice dataset and resume training for finetuning to that particular voice
Do you think this is feasible?