jamiepineandcapy-ai-staging[bot] 17fd1ddd1b refactor(generation): simplify post-generation cache cleanup ...

Initialise tts_model before the try so the finally can read its device
without a locals() probe, import empty_device_cache alongside the other
backend imports instead of inside a bare try/except, and flatten the MPS
branch in empty_device_cache.

2026-10-04 00:01:18 +00:00

..

__init__.py

Fix runaway MLX Qwen audio chunks (#964)

2026-07-26 23:31:23 -07:00

base.py

refactor(generation): simplify post-generation cache cleanup

2026-10-04 00:01:18 +00:00

chatterbox_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

chatterbox_turbo_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

hume_backend.py

fix(tada): run voice-prompt encode under torch.inference_mode (#955)

2026-07-26 23:31:20 -07:00

kokoro_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

luxtts_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

mlx_backend.py

fix(offline): patch transformers mistral-regex check to survive HF failures (#530)

2026-04-21 22:01:29 -07:00

pytorch_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

qwen_custom_voice_backend.py

fix(backend): prevent unbounded memory accumulation over consecutive TTS generations (#923)

2026-10-04 00:01:18 +00:00

qwen_llm_backend.py

fix(offline): remove process-global offline guard from Qwen3 LLM loads (#924)

2026-07-20 18:47:10 -07:00