接入 LiveKit 与 TurnSense 评分并改进模型曲线选择

2026-10-22 23:52:16 +08:00
parent c9b618e634
commit 19d4e3c767
38 changed files with 2652 additions and 58 deletions
@@ -0,0 +1,76 @@
+{
+  "model": "TurnSense 1.0 FP32",
+  "native_argmax": {
+    "n": 44,
+    "tn": 17,
+    "fp": 5,
+    "fn": 9,
+    "tp": 13,
+    "accuracy": 0.6818181818181818,
+    "false_reply_rate": 0.22727272727272727,
+    "false_hold_rate": 0.4090909090909091
+  },
+  "threshold_05": {
+    "n": 44,
+    "tn": 17,
+    "fp": 5,
+    "fn": 9,
+    "tp": 13,
+    "accuracy": 0.6818181818181818,
+    "false_reply_rate": 0.22727272727272727,
+    "false_hold_rate": 0.4090909090909091
+  },
+  "class_counts": {
+    "complete": 18,
+    "incomplete": 26
+  },
+  "load_ms": 657.7007500454783,
+  "method": "TurnSense1.0 FP32, official code/frontend/CMVN and 3-class postprocessing. CPU one intra/inter-op thread. User channel 0 int16/32768, crop received prefix BEFORE librosa resample to 16kHz, last 8s, no future ASR/audio or silence/timeout gates. Score=P(complete), native argmax complete=>1 else0; separately report threshold0.5. Full-prefix resampling is offline causal-window evaluation, not an incremental frontend benchmark.",
+  "provenance": {
+    "machine": "macOS-26.4.1-arm64-arm-64bit",
+    "hardware": "Apple M4 Mac mini CPU / 16 GB",
+    "python": "3.11.15 (main, Mar 25 2026, 02:58:47) [Clang 22.1.1 ]",
+    "dependencies": {
+      "numpy": "2.2.6",
+      "onnxruntime": "1.24.4",
+      "librosa": "0.11.0",
+      "kaldi-native-fbank": "1.22.3",
+      "soundfile": "0.13.1"
+    },
+    "providers": [
+      "CPUExecutionProvider"
+    ],
+    "intra_op_threads": 1,
+    "inter_op_threads": 1,
+    "model_manifest": {
+      "repo": "brgroup/TurnSense",
+      "revision": "341dd68c9df87d74d35b9cee63a1dcf0fff24966",
+      "version": "TurnSense1.0 FP32",
+      "code_repo": "Bairong-Xdynamics/TurnSense",
+      "code_revision": "c6d83e5b0d1355125b05eaf1b4b5c6c1acabb338",
+      "files": {
+        "model_fp32.onnx": "82256247dd38f0d9f2f213beec7ede1507347f84422fa48f29d565b613d89976",
+        "am.mvn": "29b3c740a2c0cfc6b308126d31d7f265fa2be74f3bb095cd2f143ea970896ae5"
+      },
+      "verified_against": "Hugging Face fixed revision LFS SHA256 / Git blob SHA1"
+    },
+    "script_sha256": "23215a6db3c39f6819761adf1e6cd46a8f7c0c7767d1a3640bc928ecd548b2fb",
+    "annotation_sha256": "780e50f976daf039ab976ea155bdb5d1ca5fffc792f9db7adf8063ec3048ff8e",
+    "frontend_sha256": "22808c254ea2150e290e6bdcf115322a723b67fc4e53b1ef02b8f3f42697187d",
+    "official_infer_sha256": "40295fb42a36ae4ecca30093d6bc37acbca9c75304b1a722dba73fd3b30498df"
+  },
+  "latency_ms": {
+    "preparation_ms": {
+      "p50": 1.7886869609355927,
+      "p95": 3.0542627442628145
+    },
+    "frontend_ms": {
+      "p50": 4.848978947848082,
+      "p95": 5.63460667617619
+    },
+    "inference_ms": {
+      "p50": 31.06177132576704,
+      "p95": 35.107012651860714
+    }
+  }
+}