Implemented a module to detect filler segments, and skip them for purposes of same-speaker segment coalescing

internal/filler/filler.go

@@ -0,0 +1,56 @@
+package filler
+
+import (
+	"regexp"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/seriatim/internal/model"
+)
+
+const Category = "filler"
+
+var patterns = []*regexp.Regexp{
+	regexp.MustCompile(`(?i)^(um+|uh+|er+|erm+|ah+|eh+|hmm+|mm+|mmm+)$`),
+	regexp.MustCompile(`(?i)^(um+|uh+|er+|erm+|ah+|eh+|hmm+|mm+|mmm+)(\s+(um+|uh+|er+|erm+|ah+|eh+|hmm+|mm+|mmm+))*$`),
+}
+
+// Apply tags short filler segments.
+func Apply(in model.MergedTranscript) (model.MergedTranscript, int) {
+	tagged := 0
+	for index := range in.Segments {
+		if !matches(in.Segments[index]) || hasCategory(in.Segments[index], Category) {
+			continue
+		}
+		in.Segments[index].Categories = append(in.Segments[index].Categories, Category)
+		tagged++
+	}
+	return in, tagged
+}
+
+func matches(segment model.Segment) bool {
+	text := strings.TrimSpace(segment.Text)
+	if text == "" {
+		return false
+	}
+	if len(strings.Fields(text)) > 3 {
+		return false
+	}
+	if segment.End-segment.Start > 1.0 {
+		return false
+	}
+	for _, pattern := range patterns {
+		if pattern.MatchString(text) {
+			return true
+		}
+	}
+	return false
+}
+
+func hasCategory(segment model.Segment, category string) bool {
+	for _, existing := range segment.Categories {
+		if existing == category {
+			return true
+		}
+	}
+	return false
+}