LotusGuild/cinny
3
0
Fork 0
Code Issues 27 Pull Requests 5 Actions Packages Projects Releases Wiki Activity

feat(settings): make DTLN the default ML noise-suppression model #482

Merged
jared merged 1 commits from feat/denoise-dtln-default into lotus 2026-10-30 15:42:48 -04:00
Conversation 0 Commits 1 Files Changed 4
+30 -25
1 Commits
Author SHA1 Message Date
Lotus CIandClaude Opus 5.5 9ab01ff6f6 feat(settings): make DTLN the default ML noise-suppression model
CI / Build & Quality Checks (push) Skipped
CI / Secret scan (gitleaks) (push) Skipped
CI / Playwright smoke (e2e) (push) Skipped
CI / Secret scan (gitleaks) (pull_request) Successful in 17s
Details
CI / Build & Quality Checks (pull_request) Successful in 3m45s
Details
CI / Trigger Desktop Build (pull_request) Skipped
Details
CI / Docker image build & smoke test (pull_request) Skipped
Details
CI / Playwright smoke (e2e) (pull_request) Successful in 33m3s
Details 
Browser-native stays the overall default; this only changes which model
the ML option starts on.

Measured on real speech mixed with fan, keyboard, street and babble noise
(SNR 5/15 dB), scored against the clean voice:
- DTLN: most natural voice (best PESQ/STOI of the four), strong on fans
  and typing, ~9% of one core.
- DeepFilterNet 3: removes the most noise (typing, traffic) but voices
  can sound slightly muffled, ~30% of one core.
- RNNoise: steady noise only; little help with typing.
- Speex: barely reduces noise.
- No model removes other people talking in the background.

The model list is now ordered by recommendation, with descriptions and
ratings from these results. The "Transients" column is renamed
"Typing & clicks".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017PCb59uY3UKqDqt7B6hzd5
 2026-10-30 15:05:31 -04:00