Ettore Di Giacinto 5b0196c7d0 fix(whisper): scrub invalid UTF-8 from segment text before protobuf marshal ...

whisper.cpp can emit bytes that are not valid UTF-8 — typically a
multibyte codepoint split across token boundaries. protobuf string
fields reject those at marshal time, which would surface as a transcribe
failure. Run strings.ToValidUTF8 on the segment text before it leaves
the cgo boundary so the bad byte gets replaced with U+FFFD.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-7 [Claude Code]

2026-04-26 19:35:39 +00:00

..

acestep-cpp

chore: ⬆️ Update ace-step/acestep.cpp to e0c8d75a672fca5684c88c68dbf6d12f58754258 (#9261)

2026-04-07 00:39:24 +02:00

llm/llama

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

local-store

feat: add biometrics UI (#9524)

2026-04-24 08:50:34 +02:00

opus

feat: add distributed mode (#9124)

2026-03-30 00:47:27 +02:00

piper

fix(package.sh): drop redundant -a and -R

2026-02-05 16:39:38 +01:00

qwen3-tts-cpp

feat(qwen3tts.cpp): add new backend (#9316)

2026-04-11 23:14:26 +02:00

sam3-cpp

feat(rocm): bump to 7.x (#9323)

2026-04-12 08:51:30 +02:00

sherpa-onnx

feat: Add Sherpa ONNX backend for ASR and TTS (#8523)

2026-04-24 14:40:06 +02:00

silero-vad

fix(package.sh): drop redundant -a and -R

2026-02-05 16:39:38 +01:00

stablediffusion-ggml

chore: ⬆️ Update leejet/stable-diffusion.cpp to b8bdffc19962be7e5a84bfefeb2e31bd885b571a (#9521)

2026-04-24 15:15:15 +02:00

voxtral

feat: wire transcription for llama.cpp, add streaming support (#9353)

2026-04-14 16:13:40 +02:00

whisper

fix(whisper): scrub invalid UTF-8 from segment text before protobuf marshal

2026-04-26 19:35:39 +00:00