NSF声码器+iSTFTNet
active 2023-09-19 → 2026-02-19 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 885 days from 2023-09-19 to 2026-02-19. Pushes: 10 total, peak 6 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 16 total, peak 3 in a day. Comments: 19 total, peak 5 in a day. Stars: 191 total, peak 24 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 |
|---|---|---|---|---|
| yl4579 | 27 | 10 | 0 | 13 |
| hdmjdp | 3 | 0 | 0 | 2 |
| lliwons | 2 | 0 | 0 | 1 |
| Ryu1845 | 2 | 0 | 0 | 0 |
| lhc991025 | 2 | 0 | 0 | 1 |
| bringtree | 2 | 0 | 0 | 1 |
| taalua | 1 | 0 | 0 | 0 |
| vincentspeech | 1 | 0 | 0 | 0 |
| TechInterMezzo | 1 | 0 | 0 | 1 |
| lesswrongzh | 1 | 0 | 0 | 0 |
| hualizhou167 | 1 | 0 | 0 | 0 |
| AznamirWoW | 1 | 0 | 0 | 0 |
| hc71-yoon | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#12AznamirWoW2025-02-08 00:22interesting idea, does not really work
- Issue comment#11yl45792025-01-14 00:47can't access the Pre-Trained Models links
- Issue#11yl45792025-01-14 00:47can't access the Pre-Trained Models links
- Issue#11hualizhou1672024-12-31 03:09can't access the Pre-Trained Models links
- Issue#10taalua2024-08-10 00:25sampling rate for JDC network for use in HiFTNet
- Issue#1Ryu18452024-07-28 12:30Comparison to Vocos?
- Issue comment#9lhc9910252024-07-12 06:55train the vocoder with the song data
- Issue#9lhc9910252024-07-12 03:37train the vocoder with the song data
- Issue#7vincentspeech2024-01-28 12:10What is the version of torch?
- Issue comment#6yl45792023-10-28 05:06Language robustness of F0 network
- Issue#6yl45792023-10-28 05:06Language robustness of F0 network
- Issue comment#1yl45792023-10-28 04:59Comparison to Vocos?
- Issue#6hc71-yoon2023-10-27 05:31Language robustness of F0 predictor
- Issue comment#1TechInterMezzo2023-10-21 15:45Comparison to Vocos?
- Issue comment#1yl45792023-10-03 19:47Comparison to Vocos?
- Issue#5yl45792023-09-28 03:58The performance benefits of ` Efficient Source Generation`
- Issue comment#5yl45792023-09-28 03:58The performance benefits of ` Efficient Source Generation`
- Issue comment#5yl45792023-09-28 03:45The performance benefits of ` Efficient Source Generation`
- Issue comment#5bringtree2023-09-28 03:31The performance benefits of ` Efficient Source Generation`
- Issue#5bringtree2023-09-28 03:27The performance benefits of ` Efficient Source Generation`
- Issue comment#3yl45792023-09-27 16:03why in train.py，botch loss_disc and loss_gen use "generator_TPRLS_loss"?
- Issue#4hdmjdp2023-09-27 08:30maybe there is a error
- Issue comment#3hdmjdp2023-09-27 08:27why in train.py，botch loss_disc and loss_gen use "generator_TPRLS_loss"?
- Issue comment#3hdmjdp2023-09-27 08:26why in train.py，botch loss_disc and loss_gen use "generator_TPRLS_loss"?
- Issue comment#3lliwons2023-09-27 07:02why in train.py，botch loss_disc and loss_gen use "generator_TPRLS_loss"?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 191 stars here means stars gained during the window, not the repo's star count.