Commit Graph

  • 354cacd417 feat: ksay — Kokoro 82M local TTS replaces say (4x RTF, offline, 9 voices) main Adolfo Reyna 2026-07-14 13:37:58 -04:00
  • 2e6d6d24ce feat: Apple on-device LLM (ANE) polish replaces Ollama as primary Adolfo Reyna 2026-07-13 21:31:24 -04:00
  • 80f0bf309f feat: Apple Speech v3 + Freeflow polish + draft streaming Adolfo Reyna 2026-07-13 21:08:18 -04:00
  • a2b108a5da Refine caption display and final prompt experiments Adolfo Reyna 2026-03-17 14:00:42 -04:00
  • 7451d164b7 Tune paragraph prompts for multilingual noise Adolfo Reyna 2026-03-17 11:51:53 -04:00
  • 7da02a9697 Add LLM logging and prompt experiment harness Adolfo Reyna 2026-03-17 11:13:22 -04:00
  • 727b7701c1 Update project history with LLM debugging changes Adolfo Reyna 2026-03-17 01:21:36 -04:00
  • 96fe560f6f Align Ollama system prompts with OpenAI Adolfo Reyna 2026-03-17 01:19:28 -04:00
  • 53060918e9 Remove unsupported OpenAI temperature override Adolfo Reyna 2026-03-17 00:55:31 -04:00
  • 487cb83080 Show OpenAI API error details for LLM failures Adolfo Reyna 2026-03-17 00:54:56 -04:00
  • 0dcbef7d34 Warm up local LLM before live corrections Adolfo Reyna 2026-03-17 00:29:20 -04:00
  • 9d9ee03ca1 Clarify LLM paragraph fallback behavior Adolfo Reyna 2026-03-17 00:10:39 -04:00
  • 4380c2ef99 Clarify pipeline labels and default to qwen3.5 0.8b Adolfo Reyna 2026-03-17 00:06:47 -04:00
  • f79c4f7310 Fix main_v2 bridge and pipeline regressions Adolfo Reyna 2026-03-16 21:15:15 -04:00
  • ffeb996d7e Checkpoint current transcription pipeline state Adolfo Reyna 2026-03-16 21:11:51 -04:00
  • 50f58dbc22 feat: implement accumulative LLM paragraph engine and harden 4-process pipeline Adolfo Reyna 2026-03-15 22:05:05 -04:00
  • ca07d96ff0 feat: add advanced tuning, diarization, and LLM support to multi-process engine Adolfo Reyna 2026-03-15 19:53:36 -04:00
  • c474184169 feat: refactor transcription, translation, and distribution into multiple processes Adolfo Reyna 2026-03-15 19:46:03 -04:00
  • d2c8d19c61 chore: update .gitignore to exclude .env and log files Adolfo Reyna 2026-03-15 19:26:30 -04:00
  • 5f2738c49c feat: add speaker diarization and LLM paragraph structuring Adolfo Reyna 2026-03-15 19:25:39 -04:00
  • 7fe41ba88b Document debug session issues and quick fixes Adolfo Reyna 2026-03-09 21:54:00 -04:00
  • 711a6ce692 Add session logging and tuned runtime preset Adolfo Reyna 2026-03-09 21:33:11 -04:00
  • 4115ddfa8b feat: warm up ollama and keep post-correct model loaded Adolfo Reyna 2026-03-06 20:48:11 -05:00
  • 2b501f9cdd fix: harden post-correct prompts and add overlap drift guard Adolfo Reyna 2026-03-06 20:42:01 -05:00
  • 617f2872e7 tune: increase default local llm timeouts for stability Adolfo Reyna 2026-03-06 20:23:09 -05:00
  • 11dbc5ce9a feat: add optional speaker-change detection for line cuts Adolfo Reyna 2026-03-06 20:02:38 -05:00
  • 2881bd96dd feat: add optional llm merge-decider for smart caption revisions Adolfo Reyna 2026-03-06 19:56:07 -05:00
  • 564fcaac1a feat: add v2 post-correct mode with optional local llm Adolfo Reyna 2026-03-06 19:36:08 -05:00
  • 57366543ec fix: harden arabic terminal rtl rendering Adolfo Reyna 2026-03-06 19:25:12 -05:00
  • e3cd538dca feat: load glossary corrections from file when available Adolfo Reyna 2026-03-06 19:11:09 -05:00
  • 221267a172 feat: add intelligent english caption correction v1 Adolfo Reyna 2026-03-06 19:05:56 -05:00
  • dc86ddedbd feat: improve bridge context and translation decoding controls Adolfo Reyna 2026-03-06 18:56:21 -05:00
  • 6e94210105 docs: add potential Whisper optimizations to backlog in history.md Adolfo Reyna 2026-03-01 11:48:15 -05:00
  • 3a16e44409 docs: update history.md with Phase 13 and 14 for stability and multi-channel support Adolfo Reyna 2026-03-01 11:39:25 -05:00
  • 8f6d2a0303 feat: add multi-channel support and language filtering to focus on specific speakers Adolfo Reyna 2026-03-01 11:39:03 -05:00
  • 00231cc747 feat: add hallucination detection and watchdog for stuck transcriptions Adolfo Reyna 2026-03-01 11:15:59 -05:00
  • 2999502434 feat: include draft progress in ingestion payload when streaming is enabled Adolfo Reyna 2026-02-28 21:08:55 -05:00
  • 018539d41b feat: parameterize min silence duration and increase default to 1000ms Adolfo Reyna 2026-02-28 19:40:23 -05:00
  • 81cea12e0c Revert "feat: implement heuristic punctuation buffering for translations when context is enabled" Adolfo Reyna 2026-02-28 19:39:39 -05:00
  • f68111123d docs: update history.md with today's work (Phases 10-12) Adolfo Reyna 2026-02-28 19:37:25 -05:00
  • 8b88df8b17 feat: implement heuristic punctuation buffering for translations when context is enabled Adolfo Reyna 2026-02-28 19:36:47 -05:00
  • ce4809a2b7 feat: implement prompt caching (-c) and source language bypass (--lang) Adolfo Reyna 2026-02-28 19:21:16 -05:00
  • c519907846 fix: add missing sentencepiece dependency for translation models Adolfo Reyna 2026-02-28 19:09:14 -05:00
  • 6f60d49c7b feat: implement streaming mode (-s) and 4-bit quantization (-q) for performance Adolfo Reyna 2026-02-28 19:00:56 -05:00
  • 3c874c113c feat: add command-line arguments for lang selection, ingest toggle, and device management; add README and requirements Adolfo Reyna 2026-02-28 18:55:37 -05:00
  • 0ea605cc0c Complete history.md with Phase 9: Server Ingest Adolfo Reyna 2026-02-26 23:06:43 -05:00
  • 1403604ce0 Implement server ingest with flat JSON, background worker, and exponential backoff Adolfo Reyna 2026-02-26 23:06:24 -05:00
  • a4e17ce896 Add multiprocessing.freeze_support() to fix infinite loop in compiled binary Adolfo Reyna 2026-02-26 22:02:25 -05:00
  • ceed77af14 Document build fix in history.md Adolfo Reyna 2026-02-26 21:57:51 -05:00
  • 7ba75d89dc Fix mlx._reprlib_fix hidden import in build.sh Adolfo Reyna 2026-02-26 21:57:43 -05:00
  • 1b6f58a28e Add build script and document compilation process in history.md Adolfo Reyna 2026-02-26 21:55:33 -05:00
  • ac1582b6cd Ignore build artifacts Adolfo Reyna 2026-02-26 21:55:02 -05:00
  • 72b2d0001f Complete history.md with Phase 7 Adolfo Reyna 2026-02-26 21:44:02 -05:00
  • ae2b54da9b Support multilingual detection and bridge translation via Whisper small Adolfo Reyna 2026-02-26 21:43:50 -05:00
  • da73d4e0c7 Fix variable initialization order (vad_model defined before stream start) Adolfo Reyna 2026-02-26 21:34:07 -05:00
  • d75e19665f Allow user to select audio input device at startup Adolfo Reyna 2026-02-26 21:32:29 -05:00
  • e3bda17c7d Complete project history with Phase 6 Adolfo Reyna 2026-02-26 21:26:34 -05:00
  • 37cb45c12f Add safety limits to transcription length and translation tokens to prevent memory exhaustion Adolfo Reyna 2026-02-26 21:25:57 -05:00
  • d27543022d Update history with multi-language phase Adolfo Reyna 2026-02-26 21:18:48 -05:00
  • 3166d6e7d5 Support multiple simultaneous translation languages (ES, FR, AR) Adolfo Reyna 2026-02-26 21:18:31 -05:00
  • c4a39ef29e Add project history and decision log Adolfo Reyna 2026-02-26 21:17:22 -05:00
  • 7a47781141 Comprehensive lzma mock and sacremoses dependency for stable execution Adolfo Reyna 2026-02-26 21:14:58 -05:00
  • 88cd83f87e Fix lzma import error and use MarianMT translation Adolfo Reyna 2026-02-26 21:13:48 -05:00
  • 8e45daec87 Switch to dedicated MarianMT for cleaner, non-LLM translation Adolfo Reyna 2026-02-26 21:13:03 -05:00
  • 6f602a1868 Fix LLM model path to verified public repository Adolfo Reyna 2026-02-26 21:10:07 -05:00
  • 78322cbc8d Switch to mlx-lm for translation to avoid LZMA dependency error Adolfo Reyna 2026-02-26 21:09:34 -05:00
  • 035d6e9358 Add local translation using NLLB-200 (MPS accelerated) Adolfo Reyna 2026-02-26 21:08:08 -05:00
  • 3ce95633fc Switch to whisper-small.en-mlx model Adolfo Reyna 2026-02-26 20:59:57 -05:00
  • d1fa1ffb15 Optimize for Apple Silicon using MLX Adolfo Reyna 2026-02-26 20:57:31 -05:00
  • 8d39fda6bc Improve transcription with Silero VAD for better speech detection Adolfo Reyna 2026-02-26 20:54:38 -05:00
  • 0180b1f29e Initial commit: basic Whisper live transcription script Adolfo Reyna 2026-02-26 20:53:39 -05:00