Merge branch 'main' of https://git-lium.univ-lemans.fr/speaker/sidekit

egs/librispeech/config/custom/model.py

@@ -35,7 +35,9 @@ def build():
             feature_size = self.preprocessor.n_mfcc
             self.loss = loss
             self.speaker_number = speaker_number
-            self.param_device_detection = nn.Parameter(torch.empty(0)) # Empty parameter used to detect model device location
+            self.param_device_detection = nn.Parameter(
+                torch.empty(0)
+            )  # Empty parameter used to detect model device location
 
             self.sequence_network = nn.Sequential(
                 OrderedDict(
@@ -113,8 +115,15 @@ def build():
                - the x-vector embedding
                i.e., (loss, cce), x_vector = model([...])
             """
-            x = args["speech"].to(self.param_device_detection.device)
-            x = x.squeeze(1)
+
+            # not using data_loading_hook hook
+            # unly used for SCORING by other scrips "./local/scoring.sh"
+            if not isinstance(args, dict):
+                x = args
+            else:
+                x = args["speech"].to(self.param_device_detection.device)
+                x = x.squeeze(1)
+
             x = self.preprocessor(x)
             x = self.sequence_network(x)
             x = self.stat_pooling(x)
@@ -223,7 +232,9 @@ def build():
             key.non = key.non[ndx.trialmask]
             pmiss, pfa = sidekit.bosaris.detplot.rocch(scores[key.tar], scores[key.non])
             eer = sidekit.bosaris.detplot.rocch2eer(pmiss, pfa)
-            print(f"**Test metrics - Test EER = {eer * 100} %")
+            #  print(f"**Test metrics - Test EER = {eer * 100} %")
+            norm_eer = None  # no norm EER
+            return eer, norm_eer
 
         def new_epoch_hook(self, current_epoch, total_epoch):
             pass
@@ -281,6 +292,7 @@ def get_data_loading_hook(sessions):
 
     return _hook
 
+
 # Custom data collate for padding with zeroes
 # when the whole audio file is considered
 def collate_hook(batch):
@@ -294,9 +306,17 @@ def collate_hook(batch):
         target_spk_list.append(target)
 
     # Pad tensors lists if required and construct output data
-    out_speech = nn.utils.rnn.pad_sequence(data_speech_list, batch_first=True, padding_value=0.0)
-    out_f0 = nn.utils.rnn.pad_sequence(data_f0_list, batch_first=True, padding_value=0.0)
-    out_data_dict = {"speech": out_speech.unsqueeze(1), "F0": out_f0.unsqueeze(1), "emotion": torch.tensor(data_emotion_list)}
+    out_speech = nn.utils.rnn.pad_sequence(
+        data_speech_list, batch_first=True, padding_value=0.0
+    )
+    out_f0 = nn.utils.rnn.pad_sequence(
+        data_f0_list, batch_first=True, padding_value=0.0
+    )
+    out_data_dict = {
+        "speech": out_speech.unsqueeze(1),
+        "F0": out_f0.unsqueeze(1),
+        "emotion": torch.tensor(data_emotion_list),
+    }
     out_target = torch.tensor(target_spk_list)
 
     return out_data_dict, out_target

egs/librispeech/config/custom/training.yaml

@@ -30,7 +30,7 @@ scheduler:
 
 
 # Evaluation options
-compute_test_eer: false
+compute_test_eer: true
 log_interval: 50
 validation_frequency: 1
 

egs/librispeech/local/scoring.sh

@@ -8,7 +8,7 @@ data_dir=${2:-"./data/asv_test_libri"}
 trial_wav_scp=$data_dir/trials_wav.scp
 enroll_wav_scp=$data_dir/enrolls_wav.scp
 trials=$data_dir/trials_test
-enroll_utt2spk=$data_dir/utt2spk_enrolls_test
+enroll_utt2spk=$data_dir/enrolls_utt2spk
 
 trial_xvector_scp=$data_dir/trials_xvector.scp
 enroll_xvector_scp=$data_dir/enrolls_xvector.scp
@@ -18,13 +18,13 @@ score_file=$data_dir/cosine_scoring.txt
 extract_xvectors.py --model $model \
   --wav-scp $enroll_wav_scp \
   --out-scp $enroll_xvector_scp \
-  --device "cuda:0" &
+  --device "cuda:0"
 
 # Extract trials xvector
 extract_xvectors.py --model $model \
   --wav-scp $trial_wav_scp \
   --out-scp $trial_xvector_scp \
-  --device "cuda:1"
+  --device "cuda:0"
 
 wait
 

sidekit/nnet/xvector.py

@@ -995,12 +995,11 @@ def xtrain(dataset_description,
 
             test_eer = None
             norm_eer = None
-            if local_rank < 1:
+            if local_rank < 1 and training_opts["compute_test_eer"]:
                 if hasattr(model, 'external_model') and hasattr(model.external_model, 'test'):
-                    model.external_model.test(model_opts, dataset_opts, training_opts, device=device)
-
-            if training_opts["compute_test_eer"] and local_rank < 1:
-                test_eer, norm_eer = test_metrics(model, device, model_opts, dataset_opts, training_opts)
+                    test_eer, norm_eer = model.external_model.test(model_opts, dataset_opts, training_opts, device=device)
+                else:
+                    test_eer, norm_eer = test_metrics(model, device, model_opts, dataset_opts, training_opts)
 
             monitor.update(test_eer=test_eer,
                            norm_eer=norm_eer,