2 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
mozempk	2176206afe	fix: restore correct no_speech_thold and BeamSearch defaults ... - Revert no_speech_thold from 0.0 back to 0.6 (whisper.cpp default) 0.0 means 'suppress if p(no-speech) > 0.0' which fires on every segment, silently producing 0-segment output for all real-world audio - Revert SamplingStrategy from Greedy{best_of:5} back to BeamSearch{beam_size:5} Greedy with temperature=0.0 and best_of>1 is undefined in whisper.cpp - Restore entropy_thold=2.4 and logprob_thold=-1.0 defaults - Keep flash_attn disabled (was causing silent failures on conference audio) - Tested: 59 segments on 5 min YouTube conference audio, 29 on repair audio Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-05-05 23:50:12 +02:00
mozempk	16cb6ca661	feat: GPU-accelerated Whisper API for RTX 2080 (sm_75) ... - Pure Rust: Axum 0.7 + whisper-rs 0.13 (CUDA FFI) - Async job queue with SSE progress streaming - Webhook delivery with 5x exponential backoff - Disk-persisted job state (survives restarts) - Anti-hallucination params: no_speech_thold, entropy_thold, suppress_blank - CUDA sm_75 flags: GGML_CUDA_FORCE_MMQ, GGML_CUDA_GRAPHS, GGML_CUDA_FA_ALL_QUANTS - Configurable via env: CUDA_DEVICE, WHISPER_MODEL_PATH, PORT, DATA_DIR - Gitea Actions CI: build + push to git.sal.giize.com registry - Multi-stage Dockerfile with customizable CUDA_VERSION ARG Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>	2026-05-05 22:47:24 +02:00