hailin
/
taixf
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
taixf/backend/main/xiaozhi-server
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
..
.claude add backend code 2026-04-05 19:01:15 +00:00
config add backend code 2026-04-05 19:01:15 +00:00
core fix: use full onnx model with 8 threads for fast local TTS 2026-04-05 22:53:59 -07:00
data add backend code 2026-04-05 19:01:15 +00:00
performance_tester add backend code 2026-04-05 19:01:15 +00:00
plugins_func add backend code 2026-04-05 19:01:15 +00:00
agent-base-prompt.txt add backend code 2026-04-05 19:01:15 +00:00
app.py add backend code 2026-04-05 19:01:15 +00:00
config.yaml add backend code 2026-04-05 19:01:15 +00:00
config_from_api.yaml add backend code 2026-04-05 19:01:15 +00:00
docker-compose.yml add backend code 2026-04-05 19:01:15 +00:00
docker-compose_all.yml add backend code 2026-04-05 19:01:15 +00:00
mcp_server_settings.json add backend code 2026-04-05 19:01:15 +00:00
performance_tester.py add backend code 2026-04-05 19:01:15 +00:00
requirements.txt add backend code 2026-04-05 19:01:15 +00:00