Measure Grok Voice Transcribe 1.0 on the same samples as 2.0 - #23
Merged
Merged
Conversation
The predecessor of 2.0 and xAI's default when `model` is omitted. Same adapter, same request; registered so the generation step can be measured on the same samples instead of taken from the release note. Refs Philflow/flow.raven#7279 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Same six samples, same settings (language=de, format=true). 500 of 500 utterances, 1.50 h, USD 0.15. strict-de 6.84 / 7.51 / 8.55 / 11.16 % (avemio / fleurs / mls / voxpopuli), mean 8.52 % against 2.0's 8.15 %. The step is not uniform: 2.0 wins clearly on FLEURS and on both Swiss BLEU scores, is level on MLS, and loses on VoxPopuli plenary speech. 1.0 writes mostly lower-case without punctuation, which lifts its raw-text CER above WER on fleurs and mls-de. make verify: 35 rows reproduced. Refs Philflow/flow.raven#7279 Co-Authored-By: Claude Opus 5 (1M context) <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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #22. Registers
xai/grok-voice-transcribe-1.0(same adapter) and publishes it on the benchmark page's six samples, so the generation step is measured, not assumed.make verify: 35 rows reproduced.pytest tests/test_xai_adapter.py tests/test_harness.py: 12 passed.🤖 Generated with Claude Code