rocm-chatterbox-whisper

Go to file

Build ROCm Image / build (push) Successful in 3m27s

Details

Merge main into dev and suppress MIOpen workspace warnings

- Merge: voice conditionals cache and warmup pre-computation from main
- Add MIOPEN_LOG_LEVEL=2 to suppress GemmFwdRest workspace=0 warnings

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-06 17:41:54 -04:00

.gitea/workflows

Fix image tagging: dev branch tags as dev, not latest

2026-04-06 17:29:59 -04:00

.gitignore

Initial implementation: Chatterbox TTS with ROCm and Wyoming

2026-04-05 09:51:09 -04:00

config.py

Multi-pass warmup and smaller chunk_size to fix HA timeout

2026-04-05 15:04:46 -04:00

config.yaml

Upgrade to ROCm 7.2, Python 3.11, PyTorch 2.11.0

2026-04-06 17:09:56 -04:00

docker-compose.yml

Merge main into dev and suppress MIOpen workspace warnings

2026-04-06 17:41:54 -04:00

Dockerfile.rocm

Upgrade to ROCm 7.2, Python 3.11, PyTorch 2.11.0

2026-04-06 17:09:56 -04:00

engine.py

Revert FP16 autocast — increases TTFA on first request

2026-04-05 20:30:49 -04:00

main.py

Cache voice conditionals and add FP16 autocast

2026-04-05 20:22:13 -04:00

perth_stub.py

Replace resemble-perth with a no-op stub

2026-04-05 11:16:08 -04:00

requirements-rocm-init.txt

Upgrade to ROCm 7.2, Python 3.11, PyTorch 2.11.0

2026-04-06 17:09:56 -04:00

requirements-rocm.txt

Upgrade to ROCm 7.2, Python 3.11, PyTorch 2.11.0

2026-04-06 17:09:56 -04:00

wyoming_handler.py

Add per-event logging and top-level exception catching

2026-04-05 17:10:32 -04:00

wyoming_voices.py

Add supports_synthesize_streaming=True to TtsProgram

2026-04-05 16:52:02 -04:00