Use SpikeInterface-ported models in doc

Author: alejoe91

examples/tutorials/curation/plot_1_automated_curation.py

@@ -209,8 +209,8 @@ def calculate_moving_avg(label_df, confidence_label, window_size):
 # trained on real data.
 #
 # For example, the following classifiers are trained on Neuropixels data from 11 mice recorded in
-# V1,SC and ALM: https://huggingface.co/AnoushkaJain3/noise_neural_classifier/ and
-# https://huggingface.co/AnoushkaJain3/sua_mua_classifier/ . One will classify units into
+# V1,SC and ALM: https://huggingface.co/SpikeInterface/UnitRefine_noise_neural_classifier/ and
+# https://huggingface.co/SpikeInterface/UnitRefine_sua_mua_classifier/. One will classify units into
 # `noise` or `not-noise` and the other will classify the `not-noise` units into single
 # unit activity (sua) units and multi-unit activity (mua) units.
 #
@@ -221,8 +221,8 @@ def calculate_moving_avg(label_df, confidence_label, window_size):
 
 # Apply the noise/not-noise model
 noise_neuron_labels = sc.auto_label_units(
-    sorting_analyzer = sorting_analyzer,
-    repo_id = "AnoushkaJain3/noise_neural_classifier",
+    sorting_analyzer=sorting_analyzer,
+    repo_id="SpikeInterface/UnitRefine_noise_neural_classifier",
     trust_model=True,
 )
 
@@ -231,8 +231,8 @@ def calculate_moving_avg(label_df, confidence_label, window_size):
 
 # Apply the sua/mua model
 sua_mua_labels = sc.auto_label_units(
-    sorting_analyzer = analyzer_neural,
-    repo_id = "AnoushkaJain3/sua_mua_classifier",
+    sorting_analyzer=analyzer_neural,
+    repo_id="SpikeInterface/UnitRefine_sua_mua_classifier",
     trust_model=True,
 )