Dear Deeplearning Community,
Greetings from Ethiopia! I am Walelign, and I’m engaged in a text-to-speech project. I’ve successfully compiled a 25-hour aligned text and audio corpus and have commenced the project. However, I’ve encountered some technical challenges.
I’m eager to connect with experts who have experience working on projects similar to mine, specifically involving Tacotron2 with WaveGlow or SpeechT5. Your insights and collaboration in addressing these challenges would be immensely valuable.
Looking forward to the discussion.
Best,
Walelign