Local STT CUDA failures and CPU fallback handling
NousResearch/hermes-agent · cluster 2885 · agent
Data as of
Nothing open on GitHub. Fix merged in #20897. Check it covers your case.
The short answer
- Known?
- Yes. 12 related items grouped here, 6 issues already closed.
- Fix event
- A fix was merged to main in PR #20897. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
partially resolved, deciding PRs #20897, #73510. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items concern local speech-to-text crashing or failing to fall back to CPU when CUDA or cuBLAS libraries are unavailable, misconfigured, or unsupported (e.g., Apple Silicon, WSL2, Blackwell GPUs). Several also touch TUI voice mode stability and related transcription robustness issues.
Open issues0
Open PRs0
Fixes on record
-
#20897 fix(tui): restore voice push-to-talk parity
files:
hermes_cli/voice.py,tests/hermes_cli/test_voice_wrapper.py,tests/test_tui_gateway_server.py,tui_gateway/server.py,ui-tui/src/__tests__/useInputHandlers.test.ts,ui-tui/src/app/useInputHandlers.ts,ui-tui/src/gatewayTypes.ts -
#73510 fix(stt): provider robustness — device config, CUDA fallbacks, container normalization (SILK/m4a), lazy-install recovery
files:
contributors/emails/[redacted:email],contributors/emails/[redacted:email],contributors/emails/[redacted:email],contributors/emails/[redacted:email],contributors/emails/[redacted:email],contributors/emails/[redacted:email],gateway/run.py,tests/gateway/test_stt_config.py,tests/tools/test_managed_media_gateways.py,tests/tools/test_transcription_command_providers.py,tests/tools/test_transcription_plugin_dispatch.py,tests/tools/test_transcription_tools.py,tests/tools/test_tts_pythonpath_fallback.py,tests/tools/test_voice_mode.py,tools/lazy_deps.py,tools/transcription_tools.py,tools/tts_tool.py,tools/voice_mode.py
4 PRs closed without merging
From the close comments: merged via another change 1 · stale or abandoned 1 · other 2
- #2890 fix: graceful CUDA fallback for local STT (fixes #2885) · stale or abandoned
- #13571 fix(stt): reuse CPU fallback after CUDA runtime failure · other
- #16189 fix(tui): restore classic CLI voice push-to-talk parity · other
-
#28624 fix: avoid local STT crash on Apple Silicon · merged via another change →
c0c5dac,#73510
Closed issues · 6
- Closed#2885[Bug]: Local STT crashes with RuntimeError on systems without system-wide CUDA 12 libs (WSL2, venv-only CUDA)
- Closed#6102Question: should local STT retry on CPU int8 when faster-whisper hits cuBLAS runtime errors?
- Closed#13568[Bug]: Local STT should reuse CPU fallback after cuBLAS runtime failure
- Closed#15462TUI voice mode: Python crash on 2nd transcription (cTranslate2/OpenBLAS threading conflict)
- Closed#17526STT: faster-whisper CUBLAS_STATUS_NOT_SUPPORTED on RTX 5090 (Blackwell sm_120) bypasses CPU fallback
- Closed#28622Gateway voice notes crash Python on Apple Silicon/Rosetta local STT
How this cluster was grouped
-
Link evidence (
partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text. - Members outside that structural core may belong to a different underlying problem.
-
Pairwise link density
0.14: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the Lab