update timespoken for multi

state.py

@@ -715,97 +715,24 @@ def analyze(inFileName):
         printV("Loaded results", 4)
 
         pipeline = st.session_state.pipeline
-        # For annotation-only files (RTTM/TXT/CSV), annotationToNoiseList
-        # misclassifies almost everything as multiVoice because the window-based
-        # classifier sees >2 speakers in every window. Instead derive voice
-        # categories directly from the annotation's segment gaps — more accurate
-        # and consistent for demo/pre-labeled files.
-        _is_annotation_file = inFileName.lower().endswith((".rttm", ".txt", ".csv"))
-        if _is_annotation_file:
-            from pyannote.core import Annotation, Segment
-            from collections import defaultdict
+        try:
+            noVoice, oneVoice, multiVoice = su.calcSpeakingTypes(pipeline, currAnnotation, currTotalTime)
+        except Exception as e:
+            print(f"calcSpeakingTypes failed ({e}), falling back to annotation-based voice split")
+            # Fall back: build a clean annotation containing only properly named
+            # speakers (non-None, non-empty) so build_df5 never receives None labels.
+            from pyannote.core import Annotation
             noVoice    = Annotation()
             multiVoice = Annotation()
             oneVoice   = Annotation()
-            all_segs = sorted(
-                [(seg.start, seg.end, label)
-                 for label in currAnnotation.labels()
-                 if label is not None and str(label).strip() != ""
-                 for seg in currAnnotation.subset([label]).itersegments()],
-                key=lambda x: x[0]
-            )
-            # Detect multi-voice: pairwise overlaps between speakers
-            speaker_segs = defaultdict(list)
-            for start, end, label in all_segs:
-                speaker_segs[label].append((start, end))
-            multi_intervals = []
-            labels_list = list(speaker_segs.keys())
-            for i in range(len(labels_list)):
-                for j in range(i+1, len(labels_list)):
-                    for s1, e1 in speaker_segs[labels_list[i]]:
-                        for s2, e2 in speaker_segs[labels_list[j]]:
-                            ov_s, ov_e = max(s1, s2), min(e1, e2)
-                            if ov_e > ov_s + 0.05:
-                                multi_intervals.append((ov_s, ov_e))
-            multi_intervals.sort()
-            merged_multi = []
-            for s, e in multi_intervals:
-                if merged_multi and s <= merged_multi[-1][1]:
-                    merged_multi[-1] = (merged_multi[-1][0], max(merged_multi[-1][1], e))
-                else:
-                    merged_multi.append([s, e])
-            for s, e in merged_multi:
-                active = sorted({label for start, end, label in all_segs
-                                 if start < e and end > s})
-                mv_label = '+'.join(active) if active else 'overlap'
-                multiVoice[Segment(s, e)] = mv_label
-            # No Voice: gaps in the union of all speech
-            speech_union = []
-            for start, end, _ in all_segs:
-                if speech_union and start <= speech_union[-1][1]:
-                    speech_union[-1] = (speech_union[-1][0], max(speech_union[-1][1], end))
-                else:
-                    speech_union.append([start, end])
-            prev_end = 0.0
-            for s, e in speech_union:
-                if s > prev_end + 0.1:
-                    noVoice[Segment(prev_end, s)] = 'silence'
-                prev_end = e
-            if currTotalTime > prev_end + 0.1:
-                noVoice[Segment(prev_end, currTotalTime)] = 'silence'
-            # Single Voice: segments not overlapping any multi-voice region
-            for start, end, label in all_segs:
-                if not any(ms < end and me > start for ms, me in merged_multi):
-                    oneVoice[Segment(start, end)] = label
-        else:
-            try:
-                noVoice, oneVoice, multiVoice = su.calcSpeakingTypes(pipeline, currAnnotation, currTotalTime)
-            except Exception as e:
-                print(f"calcSpeakingTypes failed ({e}), falling back to annotation-based voice split")
-                from pyannote.core import Annotation, Segment
-                noVoice    = Annotation()
-                multiVoice = Annotation()
-                oneVoice   = Annotation()
-                all_segs = sorted(
-                    [(seg.start, seg.end, label)
-                     for label in currAnnotation.labels()
-                     if label is not None and str(label).strip() != ""
-                     for seg in currAnnotation.subset([label]).itersegments()],
-                    key=lambda x: x[0]
-                )
-                prev_end = 0.0
-                for start, end, label in all_segs:
-                    if start > prev_end + 0.1:
-                        noVoice[Segment(prev_end, start)] = 'silence'
-                    oneVoice[Segment(start, end)] = label
-                    prev_end = max(prev_end, end)
-                if currTotalTime > prev_end + 0.1:
-                    noVoice[Segment(prev_end, currTotalTime)] = 'silence' 
+            for label in currAnnotation.labels():
+                if label is not None and str(label).strip() != "":
+                    for seg in currAnnotation.subset([label]).itersegments():
+                        oneVoice[seg] = label
         sumNoVoice    = su.sumTimes(noVoice)
         sumOneVoice   = su.sumTimes(oneVoice)
         sumMultiVoice = su.sumTimes(multiVoice)
 
-
         # df3
         df3 = utils.build_df3(noVoice, oneVoice, multiVoice)
         st.session_state.summaries[inFileName]["df3"] = df3
@@ -838,6 +765,10 @@ def analyze(inFileName):
             currTotalTime,
         )
         st.session_state.summaries[inFileName]["df2"] = df2
+
+        # Per-speaker multi-voice seconds — stored for the bar chart overlay
+        mv_speakers, mv_times = su.sumMultiTimesPerSpeaker(multiVoice)
+        st.session_state.summaries[inFileName]["mv_per_speaker"] = dict(zip(mv_speakers, mv_times))
         printV("Set df2", 4)
 
     except Exception as e: