scott a196294d4a Fix Wyoming protocol: remove SynthesizeStopped from Synthesize path ...

The plain Synthesize event (HA's standard TTS path) should NOT be
followed by SynthesizeStopped. That event belongs only to the streaming
protocol (SynthesizeStart/Chunk/Stop). Sending it after Synthesize
confuses HA's Wyoming client, causing it to hang indefinitely.

Also:
- Guard Synthesize path against duplicate events during streaming
- Send audio as one AudioChunk per sentence (matches working reference)
- Remove numpy import (no longer needed)

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

2026-04-05 16:22:47 -04:00

.gitea/workflows

Switch to inline cache to avoid registry blob size limits

2026-04-05 12:14:35 -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

Multi-pass warmup and smaller chunk_size to fix HA timeout

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

docker-compose.yml

Fix MIOpen MLIR kernel compilation crash during benchmark search

2026-04-05 14:21:32 -04:00

Dockerfile.rocm

Remove custom MIOpen cache path — let MIOpen use its defaults

2026-04-05 14:04:05 -04:00

engine.py

Fix warmup text length and ve attribute for torch.compile

2026-04-05 14:51:08 -04:00

main.py

Multi-pass warmup and smaller chunk_size to fix HA timeout

2026-04-05 15:04:46 -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

Pin base image to rocm/dev-ubuntu-22.04:7.2, restore torch 2.11.0

2026-04-05 12:35:58 -04:00

requirements-rocm.txt

Replace resemble-perth with a no-op stub

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

wyoming_handler.py

Fix Wyoming protocol: remove SynthesizeStopped from Synthesize path

2026-04-05 16:22:47 -04:00

wyoming_voices.py

Fix TtsVoice missing required version argument

2026-04-05 11:52:14 -04:00

Description

No description provided

213 KiB

Languages

Python 100%