The tool and AMD GPU setups break TTS training
GPU training and inference fail or lack support across the tool's versions, driver setups and AMD Radeon cards.
Tier II · Emerging Problems that are still building up.
3 public reports · first reported 18 October 2025 · last reported 21 July 2026
What's going wrong
People trying to train or run Coqui TTS models on GPUs hit version conflicts: newer builds of PyTorch do not match the XTTS requirements, an RTX 3060 setup throws device-side asserts during fine-tuning, and AMD Radeon owners ask whether any support exists.
AI-assisted: written with the help of AI from the reports. The idea report has the full summary.
In the idea report
- The full summary.
- The products the 3 reports are about, and how many came each month.
- Related problems.
No business has been found with this problem yet, so the report has no contacts. All sales are final — no refunds. Pricing.