From b1c8ac7de62c5969343352f2d10a31ebe5a107fd Mon Sep 17 00:00:00 2001
From: Nguyen Binh <nguyenvulebinh@gmail.com>
Date: Thu, 11 Apr 2024 16:01:20 +0200
Subject: [PATCH] Change alignment model for Vietnamese language

Since the current model is a wav2vec2 pre-trained model for Vietnamese audio, it won't work with alignment tasks. To make it work as expected, I recommend chaining to a fine-tuned ASR version.
---
 whisperx/alignment.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/whisperx/alignment.py b/whisperx/alignment.py
index ae9f997..765cb82 100644
--- a/whisperx/alignment.py
+++ b/whisperx/alignment.py
@@ -52,7 +52,7 @@ DEFAULT_ALIGN_MODELS_HF = {
     "tr": "mpoyraz/wav2vec2-xls-r-300m-cv7-turkish",
     "da": "saattrupdan/wav2vec2-xls-r-300m-ftspeech",
     "he": "imvladikon/wav2vec2-xls-r-300m-hebrew",
-    "vi": 'nguyenvulebinh/wav2vec2-base-vi',
+    "vi": 'nguyenvulebinh/wav2vec2-base-vi-vlsp2020',
     "ko": "kresnik/wav2vec2-large-xlsr-korean",
     "ur": "kingabzpro/wav2vec2-large-xls-r-300m-Urdu",
     "te": "anuragshas/wav2vec2-large-xlsr-53-telugu",