Repository navigation
Add Qwen3-ForcedAligner-Ultra as a forced aligner option - #16821
Merged
Merged
Conversation
Ultra (17slever17, Apache-2.0) is Qwen3-ForcedAligner-0.6B fine-tuned on hand-corrected word boundaries. Same architecture and timestamp head, so CrispASR runs cstr's F16 GGUF through its existing Qwen3 aligner path. Offered next to the 0.6B aligner in Speech to text, Import plain text and Improve time codes; the 0.6B stays the default. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds Qwen3-ForcedAligner-Ultra (Apache-2.0) as a forced aligner choice.
Ultra is
Qwen/Qwen3-ForcedAligner-0.6Bfine-tuned on ~70 h of hand-corrected word boundaries. It has the same config, timestamp head and weight size as the base model, so CrispASR runs cstr's F16 GGUF through its existing Qwen3 aligner path. No CrispASR bump is needed. The author reports a mean boundary error of 35 ms vs 125 ms for the 0.6B, at the same speed; we have not verified this.ForcedAlignerOption.Qwen3Ultra()(qwen3-forced-ultra, 1.84 GB).Tested:
ImproveTimeCodesAlignersTests(14 passed, ranking cases updated, round-trip test added).crispasr --align-onlywith the Ultra GGUF onjfk.wav: 1.9 s on Apple Silicon. Word timings are within one 80 ms step of the 0.6B aligner.🤖 Generated with Claude Code