From: Ikko Ashimine <redacted>
Date: Fri, 30 Dec 2022 17:51:08 +0000 (+0900)
Subject: models : fix typo in convert-h5-to-ggml.py
X-Git-Tag: upstream/1.7.4~1667
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=3467230a77f5444eec9e673ec465a814a0467c8d;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

models : fix typo in convert-h5-to-ggml.py

signficant -> significant
---

diff --git a/models/convert-h5-to-ggml.py b/models/convert-h5-to-ggml.py
index b882c4d4..b06ad23d 100644
--- a/models/convert-h5-to-ggml.py
+++ b/models/convert-h5-to-ggml.py
@@ -56,7 +56,7 @@ def bytes_to_unicode():
     The reversible bpe codes work on unicode strings.
     This means you need a large # of unicode characters in your vocab if you want to avoid UNKs.
     When you're at something like a 10B token dataset you end up needing around 5K for decent coverage.
-    This is a signficant percentage of your normal, say, 32K bpe vocab.
+    This is a significant percentage of your normal, say, 32K bpe vocab.
     To avoid that, we want lookup tables between utf-8 bytes and unicode strings.
     And avoids mapping to whitespace/control characters the bpe code barfs on.
     """