Hey everyone, I'm really struggling to set up CoquiTTS. I'm pretty much a beginner when it comes to Python, and despite the tons of guides out there, I've had no luck getting Text-to-Speech working. I keep running into various errors, and I'm not sure how to fix them. I'm looking for someone who can guide me through the setup process step by step, because I feel like I've tried all the solutions and I'm still stuck. Any help would be greatly appreciated!
2 Answers
I feel you—CoquiTTS can be frustrating to set up. Double-check that your system meets all the requirements, especially for CUDA. If all else fails, try reaching out on their GitHub issues page; the community there is usually really helpful!
It sounds like you're running into issues with PyTorch and its dependencies like Torchaudio and TorchCodec. These can be tricky, especially if your CUDA capability isn't right for what you're trying to do. Make sure your PyTorch installation matches your CUDA version. It's also a good idea to create a virtual environment to avoid any package conflicts. Have you tried that?
I haven’t set up a virtual environment yet. Would that really help? I just want to get TTS working!