Implementation of Fish Audio S2 Pro model inference in native ggml.
active 2026-03-17 → 2026-06-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 79 days from 2026-03-17 to 2026-06-03. Pushes: 17 total, peak 3 in a day. Pull requests: 9 total, peak 3 in a day. Issues: 6 total, peak 1 in a day. Comments: 23 total, peak 9 in a day. Stars: 9 total, peak 3 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 |
|---|---|---|---|---|
| rodrigomatta | 32 | 17 | 2 | 11 |
| subspecs | 9 | 0 | 3 | 6 |
| ivanodintsov | 2 | 0 | 1 | 1 |
| wangxuefei-25 | 2 | 0 | 0 | 2 |
| RobViren | 1 | 0 | 1 | 0 |
| persey01 | 1 | 0 | 0 | 0 |
| kolulu23 | 1 | 0 | 0 | 1 |
| Sabut0l | 1 | 0 | 0 | 1 |
| cheezwiz789 | 1 | 0 | 0 | 1 |
| anhedonialex | 1 | 0 | 1 | 0 |
| SENPAI-code66 | 1 | 0 | 0 | 0 |
| felipeov1 | 1 | 0 | 1 | 0 |
| VladimirGav | 1 | 0 | 0 | 0 |
| Qxy0happy | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#26subspecs2026-04-14 03:41
- Pull request#24subspecs2026-04-14 02:41
- Issue#25Qxy0happy2026-04-13 01:05[BUG] CUDA fallback disables all quantized GPU models including Q8 unnecessarily
- Issue comment#26subspecs2026-04-12 22:16Fix Model Prefill issue with Reference Audio
- Issue comment#25rodrigomatta2026-04-12 21:58[BUG] CUDA fallback disables all quantized GPU models including Q8 unnecessarily
- Issue comment#26subspecs2026-04-12 21:15Fix Model Prefill issue with Reference Audio
- Issue comment#25subspecs2026-04-12 18:12[BUG] CUDA fallback disables all quantized GPU models including Q8 unnecessarily
- Issue comment#7subspecs2026-04-12 15:25Added function export API
- Issue comment#24subspecs2026-04-12 13:04Fix WIN32/MSVC build errors and WIN32/MSVC patch issues
- Pull request#23anhedonialex2026-04-12 04:32
- Issue comment#22rodrigomatta2026-04-12 02:17Docker image available: s2-tts with Q8_0 GGUF for 12GB VRAM
- Issue comment#15rodrigomatta2026-04-12 00:46Save voices and other improvements
- Issue comment#13rodrigomatta2026-04-12 00:31[BUG] ggml_cuda_get_rows_switch_src0_type: unsupported src0 type: q4_K
- Issue#13rodrigomatta2026-04-12 00:20[BUG] ggml_cuda_get_rows_switch_src0_type: unsupported src0 type: q4_K
- Issue comment#20rodrigomatta2026-04-11 23:25Please update ggml submodule to fix Vulkan build
- Issue#20rodrigomatta2026-04-11 23:25Please update ggml submodule to fix Vulkan build
- Pull request#17felipeov12026-04-11 23:06
- Pull request#7subspecs2026-04-11 23:02
- Issue comment#15kolulu232026-04-11 16:44Save voices and other improvements
- Issue comment#21cheezwiz7892026-04-10 22:20GPU-based decoding optimization (CUDA)
- Issue comment#21Sabut0l2026-04-09 19:47GPU-based decoding optimization (CUDA)
- Issue comment#19wangxuefei-252026-04-09 02:05只输入文本的时候，如何固定说话人
- Issue comment#19rodrigomatta2026-04-09 01:56只输入文本的时候，如何固定说话人
- Issue comment#18wangxuefei-252026-04-09 01:40请问是否能提供模型转换成gguf格式的代码
- Issue comment#18rodrigomatta2026-04-09 01:36请问是否能提供模型转换成gguf格式的代码
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 9 stars here means stars gained during the window, not the repo's star count.