From 45ac0b2504768ae22110d6768ce7a598d2793e02 Mon Sep 17 00:00:00 2001
From: prajwal-andanur <135839136+prajwalandanur@users.noreply.github.com>
Date: Fri, 12 Jul 2024 14:14:20 +0530
Subject: [PATCH] Create Indian version for vosk-model

I have added few commands that could be used to install an Indian version vosk model which has profoundly built to capture the Indian speech accent
---
 Indian version for vosk-model | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100644 Indian version for vosk-model

diff --git a/Indian version for vosk-model b/Indian version for vosk-model
new file mode 100644
index 0000000..fdd5883
--- /dev/null
+++ b/Indian version for vosk-model	
@@ -0,0 +1,15 @@
+Use this to install indian version of vosk model from alphacephei.com
+This model is of 1 GB size only for the high-accuracy transcription on the server. 
+This indian version of vosl model can require up to 16Gb in memory since they apply advanced AI algorithms.
+Ideally you run them on some high-end servers like i7 or latest AMD Ryzen.
+.
+.
+.
+pip3 install vosk
+git clone https://github.com/prajwalandanur/offline-speech-to-text-.git
+cd nerd-dictation
+wget https://alphacephei.com/kaldi/models/vosk-model-en-in-0.5.zip
+unzip vosk-model-en-in-0.5.zip
+mv vosk-model-en-in-0.5 model
+
+