From 02aa851a4910201f0db56960064d7e121a01002c Mon Sep 17 00:00:00 2001
From: Jong Wook Kim <jongwook@nyu.edu>
Date: Tue, 15 Nov 2022 16:25:11 -0800
Subject: [PATCH] fix to return only the text token ids

---
 whisper/transcribe.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/whisper/transcribe.py b/whisper/transcribe.py
index 654f7b419..a4c3326ca 100644
--- a/whisper/transcribe.py
+++ b/whisper/transcribe.py
@@ -157,7 +157,7 @@ def add_segment(
                 "start": start,
                 "end": end,
                 "text": text,
-                "tokens": result.tokens,
+                "tokens": text_tokens.tolist(),
                 "temperature": result.temperature,
                 "avg_logprob": result.avg_logprob,
                 "compression_ratio": result.compression_ratio,