wx44wx/AI-VideoAssistant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update default.yaml configuration for speech agent parameters, adjusting min_speech_duration_ms from 100 to 120 ms and eou_threshold_ms from 800 to 1300 ms. Modify audio model parameters: set start_min_speech_ms to 100 ms, pre_speech_ms to 360 ms, and final_tail_ms to 180 ms for improved audio processing.

Browse Source
This commit is contained in:
Xin Wang
2026-02-27 09:00:38 +08:00
parent 0f02de5fc3
commit e14eac347f
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
engine/agents/default.yaml
View File

@@ -7,8 +7,8 @@ agent:
type: silero type: silero
model_path: data/vad/silero_vad.onnx model_path: data/vad/silero_vad.onnx
threshold: 0.5 threshold: 0.5
min_speech_duration_ms: 100 min_speech_duration_ms: 120
eou_threshold_ms: 800 eou_threshold_ms: 1300
llm: llm:
# provider: openai | openai_compatible | siliconflow # provider: openai | openai_compatible | siliconflow
@@ -45,9 +45,9 @@ agent:
model: FunAudioLLM/SenseVoiceSmall model: FunAudioLLM/SenseVoiceSmall
interim_interval_ms: 500 interim_interval_ms: 500
min_audio_ms: 300 min_audio_ms: 300
start_min_speech_ms: 160 start_min_speech_ms: 100
pre_speech_ms: 240 pre_speech_ms: 360
final_tail_ms: 120 final_tail_ms: 180
duplex: duplex:
enabled: true enabled: true