Commit Graph

41 Commits

Author SHA1 Message Date
Adolfo Reyna 221267a172 feat: add intelligent english caption correction v1 2026-03-06 19:05:56 -05:00
Adolfo Reyna dc86ddedbd feat: improve bridge context and translation decoding controls 2026-03-06 18:56:21 -05:00
Adolfo Reyna 6e94210105 docs: add potential Whisper optimizations to backlog in history.md 2026-03-01 11:48:15 -05:00
Adolfo Reyna 3a16e44409 docs: update history.md with Phase 13 and 14 for stability and multi-channel support 2026-03-01 11:39:25 -05:00
Adolfo Reyna 8f6d2a0303 feat: add multi-channel support and language filtering to focus on specific speakers 2026-03-01 11:39:03 -05:00
Adolfo Reyna 00231cc747 feat: add hallucination detection and watchdog for stuck transcriptions 2026-03-01 11:15:59 -05:00
Adolfo Reyna 2999502434 feat: include draft progress in ingestion payload when streaming is enabled 2026-02-28 21:08:55 -05:00
Adolfo Reyna 018539d41b feat: parameterize min silence duration and increase default to 1000ms 2026-02-28 19:40:23 -05:00
Adolfo Reyna 81cea12e0c Revert "feat: implement heuristic punctuation buffering for translations when context is enabled" 2026-02-28 19:39:39 -05:00
Adolfo Reyna f68111123d docs: update history.md with today's work (Phases 10-12) 2026-02-28 19:37:25 -05:00
Adolfo Reyna 8b88df8b17 feat: implement heuristic punctuation buffering for translations when context is enabled 2026-02-28 19:36:47 -05:00
Adolfo Reyna ce4809a2b7 feat: implement prompt caching (-c) and source language bypass (--lang) 2026-02-28 19:21:16 -05:00
Adolfo Reyna c519907846 fix: add missing sentencepiece dependency for translation models 2026-02-28 19:09:14 -05:00
Adolfo Reyna 6f60d49c7b feat: implement streaming mode (-s) and 4-bit quantization (-q) for performance 2026-02-28 19:00:56 -05:00
Adolfo Reyna 3c874c113c feat: add command-line arguments for lang selection, ingest toggle, and device management; add README and requirements 2026-02-28 18:55:37 -05:00
Adolfo Reyna 0ea605cc0c Complete history.md with Phase 9: Server Ingest 2026-02-26 23:06:43 -05:00
Adolfo Reyna 1403604ce0 Implement server ingest with flat JSON, background worker, and exponential backoff 2026-02-26 23:06:24 -05:00
Adolfo Reyna a4e17ce896 Add multiprocessing.freeze_support() to fix infinite loop in compiled binary 2026-02-26 22:02:25 -05:00
Adolfo Reyna ceed77af14 Document build fix in history.md 2026-02-26 21:57:51 -05:00
Adolfo Reyna 7ba75d89dc Fix mlx._reprlib_fix hidden import in build.sh 2026-02-26 21:57:43 -05:00
Adolfo Reyna 1b6f58a28e Add build script and document compilation process in history.md 2026-02-26 21:55:33 -05:00
Adolfo Reyna ac1582b6cd Ignore build artifacts 2026-02-26 21:55:02 -05:00
Adolfo Reyna 72b2d0001f Complete history.md with Phase 7 2026-02-26 21:44:02 -05:00
Adolfo Reyna ae2b54da9b Support multilingual detection and bridge translation via Whisper small 2026-02-26 21:43:50 -05:00
Adolfo Reyna da73d4e0c7 Fix variable initialization order (vad_model defined before stream start) 2026-02-26 21:34:07 -05:00
Adolfo Reyna d75e19665f Allow user to select audio input device at startup 2026-02-26 21:32:29 -05:00
Adolfo Reyna e3bda17c7d Complete project history with Phase 6 2026-02-26 21:26:34 -05:00
Adolfo Reyna 37cb45c12f Add safety limits to transcription length and translation tokens to prevent memory exhaustion 2026-02-26 21:25:57 -05:00
Adolfo Reyna d27543022d Update history with multi-language phase 2026-02-26 21:18:48 -05:00
Adolfo Reyna 3166d6e7d5 Support multiple simultaneous translation languages (ES, FR, AR) 2026-02-26 21:18:31 -05:00
Adolfo Reyna c4a39ef29e Add project history and decision log 2026-02-26 21:17:22 -05:00
Adolfo Reyna 7a47781141 Comprehensive lzma mock and sacremoses dependency for stable execution 2026-02-26 21:14:58 -05:00
Adolfo Reyna 88cd83f87e Fix lzma import error and use MarianMT translation 2026-02-26 21:13:48 -05:00
Adolfo Reyna 8e45daec87 Switch to dedicated MarianMT for cleaner, non-LLM translation 2026-02-26 21:13:03 -05:00
Adolfo Reyna 6f602a1868 Fix LLM model path to verified public repository 2026-02-26 21:10:07 -05:00
Adolfo Reyna 78322cbc8d Switch to mlx-lm for translation to avoid LZMA dependency error 2026-02-26 21:09:34 -05:00
Adolfo Reyna 035d6e9358 Add local translation using NLLB-200 (MPS accelerated) 2026-02-26 21:08:08 -05:00
Adolfo Reyna 3ce95633fc Switch to whisper-small.en-mlx model 2026-02-26 20:59:57 -05:00
Adolfo Reyna d1fa1ffb15 Optimize for Apple Silicon using MLX 2026-02-26 20:57:31 -05:00
Adolfo Reyna 8d39fda6bc Improve transcription with Silero VAD for better speech detection 2026-02-26 20:54:38 -05:00
Adolfo Reyna 0180b1f29e Initial commit: basic Whisper live transcription script 2026-02-26 20:53:39 -05:00