Sat Samples

cli/wake_word_sample_augmenter

@@ -18,6 +18,8 @@ parser.add_argument("--output-dir", type=str, help="Wake word output dir. Defaul
 # Personal inputs/outputs (NEW)
 parser.add_argument("--personal-dir", type=str, help="Personal WAV dir. Default: <data-dir>/personal_samples", required=False)
 parser.add_argument("--personal-output-dir", type=str, help="Personal features output dir. Default: <data-dir>/work/personal_augmented_features", required=False)
+parser.add_argument("--negative-dir", type=str, help="Reviewed negative WAV dir. Default: <data-dir>/negative_samples", required=False)
+parser.add_argument("--negative-output-dir", type=str, help="Reviewed negative features output dir. Default: <data-dir>/work/reviewed_negative_features", required=False)
 
 # Dataset dirs
 parser.add_argument("--mit-rirs-16k-dir", type=str, help="MIT RIR input directory. Default: <data-dir>/training_datasets/mit_rirs_16k", required=False)
@@ -57,6 +59,17 @@ if not args.personal_output_dir:
 else:
     args.personal_output_dir = os.path.realpath(args.personal_output_dir)
 
+# Reviewed negative defaults
+if not args.negative_dir:
+    args.negative_dir = os.path.join(args.data_dir, "negative_samples")
+else:
+    args.negative_dir = os.path.realpath(args.negative_dir)
+
+if not args.negative_output_dir:
+    args.negative_output_dir = os.path.join(work_dir, "reviewed_negative_features")
+else:
+    args.negative_output_dir = os.path.realpath(args.negative_output_dir)
+
 # Dataset defaults
 if not args.mit_rirs_16k_dir:
     args.mit_rirs_16k_dir = os.path.join(args.data_dir, "training_datasets", "mit_rirs_16k")
@@ -205,7 +218,7 @@ def bind_wav_generator(clips_obj: Clips, wav_dir: str):
 
     clips_obj.audio_generator = types.MethodType(audio_generator_from_wavs, clips_obj)
 
-def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str):
+def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str, *, remove_silence: bool = True):
     files = glob.glob(os.path.join(input_wav_dir, "*.wav"))
     if not files:
         print(f"ℹ️  No WAVs found for {label} in: {input_wav_dir} (skipping)")
@@ -218,7 +231,7 @@ def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str):
         input_directory=input_wav_dir,
         file_pattern="*.wav",
         max_clip_duration_s=5,
-        remove_silence=True,
+        remove_silence=remove_silence,
         random_split_seed=10,
         split_count=0.1,
     )
@@ -263,9 +276,12 @@ def generate_feature_set(input_wav_dir: str, out_root_dir: str, label: str):
 # Wake word generated/TTS features (existing behavior)
 generate_feature_set(args.input_dir, args.output_dir, "generated")
 
-# Personal features (NEW)
+# Personal features
 generate_feature_set(args.personal_dir, args.personal_output_dir, "personal")
 
+# Reviewed false-positive / hard-negative features
+generate_feature_set(args.negative_dir, args.negative_output_dir, "reviewed negatives", remove_silence=False)
+
 END_TIME = datetime.now(timezone.utc).replace(microsecond=0)
 et = END_TIME - START_TIME
 print(f"\n{'=' * 80}")

cli/wake_word_sample_trainer

@@ -111,6 +111,16 @@ else
   echo "ℹ️  No personal features found at ${PERSONAL_FEATURES_DIR}/training (continuing without personal weighting)"
 fi
 
+# Reviewed false-positive features are optional hard negatives.
+REVIEWED_NEGATIVE_FEATURES_DIR="${WORK_DIR}/reviewed_negative_features"
+HAS_REVIEWED_NEGATIVE="false"
+if [ -d "${REVIEWED_NEGATIVE_FEATURES_DIR}/training" ] ; then
+  HAS_REVIEWED_NEGATIVE="true"
+  echo "✅ Found reviewed negative features: ${REVIEWED_NEGATIVE_FEATURES_DIR}/training (will weight as hard negatives)"
+else
+  echo "ℹ️  No reviewed negative features found at ${REVIEWED_NEGATIVE_FEATURES_DIR}/training (continuing with stock negatives)"
+fi
+
 cd "${WORK_DIR}"
 
 echo "===== Starting ${TRAINING_STEPS} training steps ====="
@@ -133,6 +143,7 @@ features:
   truth: true
   type: mmap
 __PERSONAL_FEATURE_MARKER__
+__REVIEWED_NEGATIVE_FEATURE_MARKER__
 - features_dir: __NEG_SPEECH__
   penalty_weight: 1.0
   sampling_weight: 12.0
@@ -208,6 +219,22 @@ else
   sed -i -e "/__PERSONAL_FEATURE_MARKER__/d" "${YAML_PATH}"
 fi
 
+# Insert/remove reviewed hard-negative block
+if [ "${HAS_REVIEWED_NEGATIVE}" = "true" ]; then
+  reviewed_negative_block="$(cat <<EOF
+- features_dir: ${REVIEWED_NEGATIVE_FEATURES_DIR}
+  penalty_weight: 1.25
+  sampling_weight: 8.0
+  truncation_strategy: random
+  truth: false
+  type: mmap
+EOF
+)"
+  perl -0777 -i -pe "s#__REVIEWED_NEGATIVE_FEATURE_MARKER__#${reviewed_negative_block}#g" "${YAML_PATH}"
+else
+  sed -i -e "/__REVIEWED_NEGATIVE_FEATURE_MARKER__/d" "${YAML_PATH}"
+fi
+
 echo "   Wrote training_parameters.yaml"
 rm -rf "${WORK_DIR}/trained_models/wakeword"