[ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition
active 2023-08-18 → 2025-08-14 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 728 days from 2023-08-18 to 2025-08-14. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 2 in a day. Comments: 12 total, peak 2 in a day. Stars: 39 total, peak 2 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| hechengzhi985 | 6 | 0 | 0 | 2 |
| dewishyi | 3 | 0 | 0 | 3 |
| sst0715 | 2 | 0 | 0 | 1 |
| burchim | 2 | 0 | 0 | 2 |
| waiter1 | 1 | 0 | 0 | 1 |
| Rawsea | 1 | 0 | 0 | 1 |
| ZixuanNi | 1 | 0 | 0 | 1 |
| HajarMazaheri | 1 | 0 | 0 | 0 |
| 1749352011 | 1 | 0 | 0 | 1 |
| L-Absente | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#30L-Absente2025-02-21 08:30Can't enter second epoch
- Issue comment#29dewishyi2024-08-29 08:51warp_rnnt version
- Issue comment#2917493520112024-08-29 07:48warp_rnnt version
- Issue comment#29dewishyi2024-06-17 10:41warp_rnnt version
- Issue comment#29sst07152024-06-16 14:18warp_rnnt version
- Issue comment#29dewishyi2024-06-15 11:29warp_rnnt version
- Issue#29sst07152024-05-04 08:37warp_rnnt version
- Issue#28hechengzhi9852024-03-07 02:53Is it possible to use the VoxCeleb dataset for both training and evaluation?
- Issue comment#26hechengzhi9852024-03-06 09:52ctcdecode
- Issue#27hechengzhi9852024-03-06 09:49TypeError: wer() got an unexpected keyword argument 'standardize'
- Issue#28hechengzhi9852024-03-06 09:43Is it possible to use the VoxCeleb dataset for both training and evaluation?
- Issue comment#27burchim2024-01-31 17:26TypeError: wer() got an unexpected keyword argument 'standardize'
- Issue comment#27Rawsea2024-01-31 05:04TypeError: wer() got an unexpected keyword argument 'standardize'
- Issue comment#27hechengzhi9852024-01-29 08:35TypeError: wer() got an unexpected keyword argument 'standardize'
- Issue#27hechengzhi9852024-01-29 08:17TypeError: wer() got an unexpected keyword argument 'standardize'
- Issue comment#26burchim2024-01-20 04:35ctcdecode
- Issue comment#26ZixuanNi2023-12-13 13:45ctcdecode
- Issue comment#26waiter12023-11-28 08:06ctcdecode
- Issue#26HajarMazaheri2023-10-30 11:51ctcdecode
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 39 stars here means stars gained during the window, not the repo's star count.