From 6e942101053eb31f264f60b75a8af7b8c4e2b9c9 Mon Sep 17 00:00:00 2001 From: Adolfo Reyna Date: Sun, 1 Mar 2026 11:48:15 -0500 Subject: [PATCH] docs: add potential Whisper optimizations to backlog in history.md --- history.md | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/history.md b/history.md index 96e1238..de3f359 100644 --- a/history.md +++ b/history.md @@ -117,3 +117,12 @@ The project now features a high-performance, Apple Silicon-optimized pipeline th - **Stereo Channel Selection:** Added `--channels` and `--pick-channel [0|1]` flags. This allows the tool to pull a specific audio channel (e.g., English on Left, Translation on Right) from a stereo feed, ignoring the other. - **Language Filtering (`--filter-lang`):** Integrated a mechanism to discard any segment where the detected language does not match the hardcoded `--lang` parameter. - **Outcome:** Enabled the ability to "focus" the transcription engine on a single speaker even when the audio input is a complex mix. + +## Phase 15: Potential Future Optimizations (Backlog) +- **Decoding Parameters:** + - **Temperature Fallback:** Use a tuple `(0.0, 0.2, 0.4, 0.6, 0.8, 1.0)` to allow Whisper to re-try failed transcriptions with higher randomness (crucial for music/singing). + - **Beam Size Tuning:** Set `beam_size=1` for Draft Mode (3x faster) and `beam_size=5` for final segments (higher accuracy). + - **Token Suppression:** Native suppression of music symbols or common hallucination tokens at the decoder level. + - **Heuristic Thresholds:** Utilize `logprob_threshold` (confidence) and `compression_ratio_threshold` (repetition) to programmatically identify and discard bad transcriptions before they reach the user. +- **Structural Features:** + - **Word-Level Timestamps:** Enable `word_timestamps=True` to provide granular timing data for front-end caption highlighting.