hailin
/
taixf
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
taixf/backend/main/xiaozhi-server/core/providers
History
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
..
asr add backend code 2026-04-05 19:01:15 +00:00
intent add backend code 2026-04-05 19:01:15 +00:00
llm fix: clean junk text from Antaf + use int8 TTS model for speed 2026-04-05 22:52:02 -07:00
memory add backend code 2026-04-05 19:01:15 +00:00
tools add backend code 2026-04-05 19:01:15 +00:00
tts fix: use full onnx model with 8 threads for fast local TTS 2026-04-05 22:53:59 -07:00
vad add backend code 2026-04-05 19:01:15 +00:00
vllm add backend code 2026-04-05 19:01:15 +00:00