From 81c57ae40c6b2f63b18c6ad3ee5d448208752296 Mon Sep 17 00:00:00 2001
From: makaveli10 <suryanvineet47@gmail.com>
Date: Tue, 5 Nov 2024 18:11:32 +0530
Subject: [PATCH] Send completed bool with each segment

Completed bool represents if the segment is completely processed by the server

Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
---
 whisper_live/client.py |  6 +++---
 whisper_live/server.py | 13 ++++++++-----
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/whisper_live/client.py b/whisper_live/client.py
index 4cfb63c..15b6306 100644
--- a/whisper_live/client.py
+++ b/whisper_live/client.py
@@ -112,9 +112,9 @@ class Client:
         for i, seg in enumerate(segments):
             if not text or text[-1] != seg["text"]:
                 text.append(seg["text"])
-                if i == len(segments) - 1:
+                if i == len(segments) - 1 and not seg["completed"]:
                     self.last_segment = seg
-                elif (self.server_backend == "faster_whisper" and
+                elif (self.server_backend == "faster_whisper" and seg["completed"] and
                       (not self.transcript or
                         float(seg['start']) >= float(self.transcript[-1]['end']))):
                     self.transcript.append(seg)
@@ -259,7 +259,7 @@ class Client:
 
         """
         if self.server_backend == "faster_whisper":
-            if (self.last_segment):
+            if (self.last_segment) and self.transcript[-1]["text"] != self.last_segment["text"]:
                 self.transcript.append(self.last_segment)
             utils.create_srt_file(self.transcript, output_path)
 
diff --git a/whisper_live/server.py b/whisper_live/server.py
index 575a2cf..b68df5a 100644
--- a/whisper_live/server.py
+++ b/whisper_live/server.py
@@ -1001,7 +1001,7 @@ class ServeClientFasterWhisper(ServeClientBase):
                 logging.error(f"[ERROR]: Failed to transcribe audio chunk: {e}")
                 time.sleep(0.01)
 
-    def format_segment(self, start, end, text):
+    def format_segment(self, start, end, text, completed=False):
         """
         Formats a transcription segment with precise start and end times alongside the transcribed text.
 
@@ -1018,7 +1018,8 @@ class ServeClientFasterWhisper(ServeClientBase):
         return {
             'start': "{:.3f}".format(start),
             'end': "{:.3f}".format(end),
-            'text': text
+            'text': text,
+            'completed': completed
         }
 
     def update_segments(self, segments, duration):
@@ -1058,7 +1059,7 @@ class ServeClientFasterWhisper(ServeClientBase):
                 if s.no_speech_prob > self.no_speech_thresh:
                     continue
 
-                self.transcript.append(self.format_segment(start, end, text_))
+                self.transcript.append(self.format_segment(start, end, text_, completed=True))
                 offset = min(duration, s.end)
 
         # only process the segments if it satisfies the no_speech_thresh
@@ -1067,7 +1068,8 @@ class ServeClientFasterWhisper(ServeClientBase):
             last_segment = self.format_segment(
                 self.timestamp_offset + segments[-1].start,
                 self.timestamp_offset + min(duration, segments[-1].end),
-                self.current_out
+                self.current_out,
+                completed=False
             )
 
         # if same incomplete segment is seen multiple times then update the offset
@@ -1083,7 +1085,8 @@ class ServeClientFasterWhisper(ServeClientBase):
                 self.transcript.append(self.format_segment(
                     self.timestamp_offset,
                     self.timestamp_offset + duration,
-                    self.current_out
+                    self.current_out,
+                    completed=True
                 ))
             self.current_out = ''
             offset = duration