hailin
/
taixf
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12 Commits 1 Branch 0 Tags 66 MiB
Commit Graph

5 Commits

Author SHA1 Message Date
hailin 9b2b875c2b fix: run TTS synthesis in thread pool to avoid blocking event loop 
Also add size check for int8 model to skip LFS pointer files.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-05 23:05:44 -07:00
hailin 83cdf3396d fix: use full onnx model with 8 threads for fast local TTS 
Benchmark: short=0.37s, long=1.06s with 8 CPU threads.
GPU not available in pip sherpa-onnx, CPU is fast enough.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-05 22:53:59 -07:00
hailin c2727d7e08 fix: clean junk text from Antaf + use int8 TTS model for speed 
- Filter "完成资料引用" and other status text from Antaf responses
- Use int8 quantized model for faster TTS inference
- Add configurable num_threads for sherpa-onnx

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-05 22:52:02 -07:00
hailin e5599d4f43 feat: add sherpa-onnx local TTS provider 
Offline VITS TTS using sherpa-onnx, no network dependency.
Uses vits-melo-tts-zh_en model for Chinese/English.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-05 22:43:51 -07:00
hailin 742389e965 add backend code 2026-04-05 19:01:15 +00:00