Stefan Walcz 0cb6c908da fix(backends): build whisper and parakeet-cpp for ROCm GPUs ...

whisper passed -DGGML_HIPBLAS=ON, which ggml no longer knows, so the
hipblas image was a CPU-only build (same issue as #10666 in
qwen3-tts-cpp). Use GGML_HIP with the ROCm clang and forward the gfx
targets. parakeet-cpp enabled PARAKEET_GGML_HIP but did not forward
the gfx targets; forward them the same way.

Docs-Not-Needed: build flags only, no user-facing behaviour or option changes.

Assisted-by: Claude Code:claude-opus-5-5
Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>

2026-10-31 19:29:43 +01:00

..

testdata

feat(parakeet-cpp): name speakers from the shared voice registry (#12382)

2026-10-01 08:25:52 +02:00

.gitignore

feat(parakeet-cpp): add NVIDIA NeMo Parakeet ASR backend (parakeet.cpp) (#10084)

2026-05-30 14:46:10 +02:00

batcher_test.go

feat(parakeet-cpp): nemotron-3.5-asr multilingual streaming model + request language support (#10199)

2026-06-06 13:53:10 +02:00

batcher.go

feat(parakeet-cpp): nemotron-3.5-asr multilingual streaming model + request language support (#10199)

2026-06-06 13:53:10 +02:00

boundary_test.go

feat(realtime): Semantic VAD EOU token (#10444)

2026-06-30 09:01:22 +02:00

boundary.go

feat(realtime): Semantic VAD EOU token (#10444)

2026-06-30 09:01:22 +02:00

bundle_test.go

feat(parakeet-cpp): load bundle GGUF files, bundle gallery entries, pin bump (#12479)

2026-10-04 20:33:13 +02:00

bundle.go

feat(parakeet-cpp): load bundle GGUF files, bundle gallery entries, pin bump (#12479)

2026-10-04 20:33:13 +02:00

diarize_sounds_test.go

feat(diarization): return sound events with include_sounds (#12544)

2026-10-07 14:10:45 +02:00

diarize_sounds.go

feat(diarization): return sound events with include_sounds (#12544)

2026-10-07 14:10:45 +02:00

diarize_test.go

feat(audio): remember speakers from diarization (#12414)

2026-10-02 08:14:00 +02:00

diarize.go

feat(diarization): return sound events with include_sounds (#12544)

2026-10-07 14:10:45 +02:00

driver.go

feat(realtime): Semantic VAD EOU token (#10444)

2026-06-30 09:01:22 +02:00

goparakeetcpp_test.go

feat(parakeet-cpp): add the voice_verify_threshold model option

2026-10-05 23:48:20 +00:00

goparakeetcpp.go

feat(parakeet-cpp): add the voice_verify_threshold model option

2026-10-05 23:48:20 +00:00

guard_test.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

guard.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

live_test.go

feat(parakeet-cpp): name speakers from the shared voice registry (#12382)

2026-10-01 08:25:52 +02:00

live.go

feat(parakeet-cpp): name speakers from the shared voice registry (#12382)

2026-10-01 08:25:52 +02:00

main.go

feat(parakeet-cpp): serve VoiceEmbed and VoiceVerify from the speaker encoder

2026-10-05 23:46:06 +00:00

Makefile

fix(backends): build whisper and parakeet-cpp for ROCm GPUs

2026-10-31 19:29:43 +01:00

package.sh

refactor(backends): extract package-system-libs.sh from 31 package.sh (#11095)

2026-07-30 16:30:49 +02:00

profiles_test.go

fix(distributed): free only the named model on model.unload (#12537)

2026-10-06 22:44:25 +02:00

profiles.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

roles_test.go

feat(parakeet-cpp): name speakers from the shared voice registry (#12382)

2026-10-01 08:25:52 +02:00

roles.go

feat(parakeet-cpp): add the voice_verify_threshold model option

2026-10-05 23:48:20 +00:00

run.sh

fix(backends): quote $CURDIR in run.sh (fixes backends in paths with spaces) (#10519)

2026-06-26 01:02:48 +02:00

scene_test.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

scene.go

feat(diarization): return sound events with include_sounds (#12544)

2026-10-07 14:10:45 +02:00

segments_test.go

feat(realtime): Semantic VAD EOU token (#10444)

2026-06-30 09:01:22 +02:00

sound_test.go

feat(parakeet-cpp): speaker diarization, sound detection and live scene events (#12335)

2026-09-29 23:58:17 +02:00

sound.go

feat(parakeet-cpp): load bundle GGUF files, bundle gallery entries, pin bump (#12479)

2026-10-04 20:33:13 +02:00

speaker_fingerprint_test.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

speaker_real_test.go

feat(parakeet-cpp): name speakers from the shared voice registry (#12382)

2026-10-01 08:25:52 +02:00

speaker_registry_test.go

feat(audio): remember speakers from diarization (#12414)

2026-10-02 08:14:00 +02:00

speaker_registry.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

speakers_test.go

feat(parakeet-cpp): speaker diarization, sound detection and live scene events (#12335)

2026-09-29 23:58:17 +02:00

speakers.go

feat(audio): remember speakers from diarization (#12414)

2026-10-02 08:14:00 +02:00

vad_rpc_test.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

vad_test.go

feat(parakeet-cpp): Moondream Ultra and Redux gallery entries, VAD option, pin bump (#12455)

2026-10-03 22:08:12 +02:00

vad.go

feat(parakeet-cpp): encoder fingerprint for speaker naming, VAD trim and word filter options, pin bump (#12491)

2026-10-05 15:57:16 +02:00

voice_embed_test.go

feat(parakeet-cpp): add the voice_verify_threshold model option

2026-10-05 23:48:20 +00:00

voice_embed.go

feat(parakeet-cpp): add the voice_verify_threshold model option

2026-10-05 23:48:20 +00:00