From bd9d47a977f1bc0ea471ba48b95da22bcd918b0a Mon Sep 17 00:00:00 2001
From: Kathy Reid <kathy@kathyreid.id.au>
Date: Wed, 8 Oct 2025 22:43:54 +1100
Subject: [PATCH] Update tokenizer.py to fix erroneous Javanese language code

The ISO-639-1 code for Javanese is `jv` NOT `jw` as given here.
It should be listed as `jv`.
---
 whisper/tokenizer.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/whisper/tokenizer.py b/whisper/tokenizer.py
index 2af8375..4bc0984 100644
--- a/whisper/tokenizer.py
+++ b/whisper/tokenizer.py
@@ -105,7 +105,7 @@ LANGUAGES = {
     "ln": "lingala",
     "ha": "hausa",
     "ba": "bashkir",
-    "jw": "javanese",
+    "jv": "javanese",
     "su": "sundanese",
     "yue": "cantonese",
 }