Skip to content

frothywater/kanade-tokenizer

View on GitHub ↗Related repositories →

Kanade is a speech tokenizer that encodes speech into compact content tokens and global embeddings and decodes them back to mel spectrograms.

Python · active 2025-11-04 → 2026-09-11 (UTC)

Complete coverage27,933 / 27,933 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-10-21 (UTC)
Events
56
Pushes
6
Pull requests
0
Issues
2
Stars
45
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 312 days from 2025-11-04 to 2026-09-11. Pushes: 6 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 2 total, peak 1 in a day. Comments: 0 total, peak 0 in a day. Stars: 45 total, peak 8 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
frothywater6500
stephenmac71100
alephpi1000

Recent activity

Latest issues, pull requests and releases

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 45 stars here means stars gained during the window, not the repo's star count.