From 6a72b61564dbea7242b8d4eab74af375df516759 Mon Sep 17 00:00:00 2001
From: m-bain <36994049+m-bain@users.noreply.github.com>
Date: Tue, 11 Apr 2023 20:15:37 +0100
Subject: [PATCH] clamp end_timestamp to prevent infinite loop

---
 whisperx/asr.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/whisperx/asr.py b/whisperx/asr.py
index ac16459..e78d77c 100644
--- a/whisperx/asr.py
+++ b/whisperx/asr.py
@@ -269,6 +269,10 @@ def transcribe(
                     end_timestamp_pos = (
                         sliced_tokens[-1].item() - tokenizer.timestamp_begin
                     )
+                    
+                    # clamp end-time to at least be 1 frame after start-time
+                    end_timestamp_pos = max(end_timestamp_pos, start_timestamp_pos + time_precision)
+
                     current_segments.append(
                         new_segment(
                             start=time_offset + start_timestamp_pos * time_precision,
@@ -426,4 +430,4 @@ def transcribe_with_vad(
 
     output["language"] = output["segments"][0]["language"]
 
-    return output
\ No newline at end of file
+    return output