Skip to content

feat: speaking path from ASR transcript JSON (Fixes #6) - #125

Open
samuelpatak-png wants to merge 1 commit into
mergeos-bounties:masterfrom
samuelpatak-png:feat/speaking-asr-transcript-6
Open

feat: speaking path from ASR transcript JSON (Fixes #6)#125
samuelpatak-png wants to merge 1 commit into
mergeos-bounties:masterfrom
samuelpatak-png:feat/speaking-asr-transcript-6

Conversation

@samuelpatak-png

Copy link
Copy Markdown

Summary

  • Accept ASR transcript JSON (transcript/text, optional confidence 0–1 or 0–100) for skill=speaking
  • Return offline fluency score plus actionable feedback bullets
  • CLI: nokaman eval speaking --file … + fixture + app-integration docs

Test plan

  • pytest tests/test_speaking_fluency.py tests/test_cli.py ×3 clean
  • CLI fixture data/fixtures/asr_transcript_en_b1.json

Fixes #6

Made with Cursor

Adds optional ASR confidence, feedback bullets, CLI eval speaking, and
an app-integration fixture/docs path for skill=speaking transcripts.

Co-authored-by: Cursor <cursoragent@cursor.com>
@laurentketterle-hub

Copy link
Copy Markdown

QA Verification — NokaMan#125

PR: feat: speaking path from ASR transcript JSON (Fixes #6)
Author: @samuelpatak-png | SHA: d78f880

CI: no checks

  • No checks

Tests

✅ no tests

Evidence

| Screenshots | ❌ |
| Video/GIF | ❌ |
| Logs | ❌ |

Verdict: ⚠️ EVIDENCE MISSING

Auto-verified via PR Verify Tool

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[50 MRG] Speaking path: score from ASR transcript JSON

3 participants