nite/video-edit-planner-skill
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: remove unimplemented FunASR context mode

Browse Source
This commit is contained in:
nite
2026-07-14 17:45:10 +08:00
parent acfbd6d72a
commit 4181323184
2 changed files with 0 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SKILL.md
-1
View File
@@ -132,7 +132,6 @@ uv run --directory SKILL_DIR/scripts/transcription funasr-nano VIDEO_PATH --list
Where `VIDEO_DIR` is the directory containing the video file, `SKILL_DIR` is the skill installation directory, and `AUDIO_LANGUAGE_CODE` is the explicit transcription language (for example `zh` for Mandarin Chinese).
**Rolling context / semantic correction:** Fun-ASR-Nano has upstream support for `prev_text`-style rolling context in streaming/incremental examples: earlier stabilized text can be fed back as context for later decoding, similar to a 2-pass-style refinement. However, do not assume the current bundled offline script automatically enables whole-file rolling semantic correction: it currently calls ordinary `AutoModel.generate(...)` on the extracted WAV and does not run a cumulative chunked pass with `prev_text`. See `references/funasr-nano-rolling-context.md`. Treat the current transcript as a strong baseline, not the final word when unclear speech or homophones matter.
**Common OBS multi-track audio layouts.** When the user says "multi-track" or mentions OBS recording, these are the typical stream layouts: