wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updated Smart Turn model weights to v3.2

Browse Source
This commit is contained in:
marcus-daily
2026-01-07 17:23:11 +00:00
parent 54cf0116a8
commit d1bedef5b3
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
src/pipecat/audio/turn/smart_turn/data/smart-turn-v3.1-cpu.onnx → src/pipecat/audio/turn/smart_turn/data/smart-turn-v3.2-cpu.onnx
View File

Binary file not shown.

4
src/pipecat/audio/turn/smart_turn/local_smart_turn_v3.py
View File

@@ -42,7 +42,7 @@ class LocalSmartTurnAnalyzerV3(BaseSmartTurn):
Args:
smart_turn_model_path: Path to the ONNX model file. If this is not
set, the bundled smart-turn-v3.1-cpu model will be used.
set, the bundled smart-turn-v3.2-cpu model will be used.
cpu_count: The number of CPUs to use for inference. Defaults to 1.
**kwargs: Additional arguments passed to BaseSmartTurn.
"""
@@ -50,7 +50,7 @@ class LocalSmartTurnAnalyzerV3(BaseSmartTurn):
if not smart_turn_model_path:
# Load bundled model
model_name = "smart-turn-v3.1-cpu.onnx"
model_name = "smart-turn-v3.2-cpu.onnx"
package_path = "pipecat.audio.turn.smart_turn.data"
try: