From e8184ce9d1e0a8bef9f8a98ad3122d89e440988a Mon Sep 17 00:00:00 2001
From: Tahir Javed <tahirjmakhdoomi@gmail.com>
Date: Wed, 21 Aug 2024 14:22:28 +0530
Subject: [PATCH 1/2] added timeline

---
 html/asr.html | 99 +++++++++++++++++++++++++--------------------------
 1 file changed, 49 insertions(+), 50 deletions(-)

diff --git a/html/asr.html b/html/asr.html
index 6941c60..f4e8bd2 100644
--- a/html/asr.html
+++ b/html/asr.html
@@ -45,77 +45,76 @@ <h1>Automatic Speech Recognition</h1>
         <div class="container">
             <ul>
                 <li>
-                    <h3 class="heading">IndicWav2Vec</h3>
-                    <p>IndicWav2Vec is a speech model pretrained on 17,000 hours of unlabelled audio across 40 Indian
-                        languages, offering the most extensive language coverage among models tailored for Indian
-                        languages. </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                        <a href="jupyter"><img src="../assets/logos/colab.png"></i></a>
-                    <span class="date dataset">February 2021</span>
+                    <h3 class="heading">IndicVoices 2.0</h3>
+                    <p>IndicVoices 2.0 is a dataset of natural and spontaneous speech containing a total of 12000 hours of read (8%), extempore (76%) and conversational (15%) audio from 22563 speakers covering 208 Indian districts and 22 languages. Of these 12000 hours, 3200 hours have already been transcribed, with a median of 122 hours per language.</p>
+                        <a href="https://github.com/AI4Bharat/IndicVoices"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2403.01926"><img src="../assets/logos/paper.png"></a>
+                        <!-- <a href="jupyter"><img src="../assets/logos/colab.png"></i></a> -->
+                    <span class="date dataset">June 2024</span>
                     <span class="circle"></span>
                 </li>
                 <li>
-                    <h3 class="heading">Some Model</h3>
-                    <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit. Fugit excepturi accusamus minus
-                        totam </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                    <span class="date model">February 2021</span>
+                    <h3 class="heading">Lahaja</h3>
+                    <p>Lahaja is a benchmark featuring 12.5 hours of Hindi audio to facilitate a comprehensive assessment of Hindi ASR systems across various accents. This dataset includes read and spontaneous speech on diverse topics, collected from 132 speakers across 83 districts in India.</p>
+                        <a href="https://github.com/AI4Bharat/Lahaja"><img src="../assets/logos/github.png"></a>
+                        <a href="arxiv"><img src="../assets/logos/paper.png"></a>
+                    <span class="date dataset">June 2024</span>
                     <span class="circle"></span>
                 </li>
                 <li>
-                    <h3 class="heading">Some Dataset</h3>
-                    <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit. Fugit excepturi accusamus minus
-                        totam </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                    <span class="date dataset">March 2021</span>
+                    <h3 class="heading">IndicVoices 1.0</h3>
+                    <p>IndicVoices 1.0 is a dataset of natural and spontaneous speech containing a total of 7348 hours of read (9%), extempore (74%) and conversational (17%) audio from 16237 speakers covering 145 Indian districts and 22 languages. Of these 7348 hours, 1639 hours have already been transcribed, with a median of 73 hours per language.</p>
+                        <a href="https://github.com/AI4Bharat/IndicVoices"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2403.01926"><img src="../assets/logos/paper.png"></a>
+                    <span class="date dataset">March 2024</span>
                     <span class="circle"></span>
                 </li>
                 <li>
-                    <h3 class="heading">Some Model</h3>
-                    <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit. Fugit excepturi accusamus minus
-                        totam </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                    <span class="date model">April 2021</span>
+                    <h3 class="heading">Svarah</h3>
+                    <p>Svarah is a benchmark addressing gaps in ASR performance on Indian accents, featuring 9.6 hours of transcribed English audio from 117 speakers across 65 locations in India. It includes both read and spontaneous speech across various domains, ensuring diverse vocabulary.</p>
+                        <a href="https://github.com/AI4Bharat/Svarah"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2305.15760"><img src="../assets/logos/paper.png"></a>
+                    <span class="date dataset">August 2023</span>
                     <span class="circle"></span>
                 </li>
                 <li>
-                    <h3 class="heading">Some Model</h3>
-                    <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit. Fugit excepturi accusamus minus
-                        totam </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                    <span class="date model">April 2021</span>
+                    <h3 class="heading">IndicWhisper</h3>
+                    <p>IndicWhisper is finetuned on OpenAI’s Whisper model using the Vistaar-train set with over 10,000 hours across 12 Indian languages</p>
+                        <a href="https://github.com/AI4Bharat/vistaar"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2305.15386"><img src="../assets/logos/paper.png"></a>
+                    <span class="date model">July 2023</span>
                     <span class="circle"></span>
                 </li>
                 <li>
-                    <h3 class="heading">Some Dataset</h3>
-                    <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit. Fugit excepturi accusamus minus
-                        totam </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                    <span class="date dataset">April 2021</span>
+                    <h3 class="heading">Kathbath</h3>
+                    <p>Kathbath is a comprehensive dataset comprising 1,684 hours of labeled speech data collected from 1,218 contributors across 203 districts in India, spanning 12 Indian languages. </p>
+                        <a href="https://github.com/AI4Bharat/IndicSUPERB"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2208.11761"><img src="../assets/logos/paper.png"></a>
+                    <span class="date dataset">February 2023</span>
                     <span class="circle"></span>
                 </li>
                 <li>
-                    <h3 class="heading">Some Model</h3>
-                    <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit. Fugit excepturi accusamus minus
-                        totam </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                    <span class="date model">April 2021</span>
+                    <h3 class="heading">Shrutilipi</h3>
+                    <p>Shrutilipi is a dataset with 6,400+ hours of labeled audio across 12 Indian languages, totaling 4.95M sentences, created by mining text audio pairs from All India Radio.</p>
+                        <a href="https://github.com/AI4Bharat/Shrutilipi"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2208.12666"><img src="../assets/logos/paper.png"></a>
+                    <span class="date model">August 2022</span>
                     <span class="circle"></span>
                 </li>
                 <li>
-                    <h3 class="heading">Some Dataset</h3>
-                    <p>Lorem ipsum dolor sit amet, consectetur adipisicing elit. Fugit excepturi accusamus minus
-                        totam </p>
-                        <a href="github"><i class="fa-brands fa-github"></i></a>
-                        <a href="arxiv"><i class="fa-regular fa-file-pdf"></i></a>
-                    <span class="date dataset">April 2021</span>
+                    <h3 class="heading">Dhwani</h3>
+                    <p>Dhwani is a unlabelled audio dataset consisting of 17,000 hours of raw speech data for 40 Indian languages from a wide variety of domains including education, news, technology, and finance </p>
+                        <a href="https://github.com/AI4Bharat/IndicWav2Vec/tree/main/data_prep_scripts/urls"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2111.03945"><img src="../assets/logos/paper.png"></a>
+                    <span class="date dataset">February 2022</span>
+                    <span class="circle"></span>
+                </li>
+                <li>
+                    <h3 class="heading">IndicWav2Vec</h3>
+                    <p>IndicWav2Vec is a speech model pretrained on 17,000 hours of unlabelled audio across 40 Indian languages, offering the most extensive language coverage among models tailored for Indian languages. </p>
+                        <a href="https://github.com/AI4Bharat/IndicWav2Vec"><img src="../assets/logos/github.png"></a>
+                        <a href="https://arxiv.org/abs/2111.03945"><img src="../assets/logos/paper.png"></a>
+                    <span class="date model">February 2022</span>
                     <span class="circle"></span>
                 </li>
             </ul>

From 94eeb2485188ad2744da5414e934547662e57ceb Mon Sep 17 00:00:00 2001
From: Tahir Javed <tahirjmakhdoomi@gmail.com>
Date: Thu, 22 Aug 2024 12:16:00 +0530
Subject: [PATCH 2/2] updated timeline

---
 html/asr.html | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/html/asr.html b/html/asr.html
index f4e8bd2..980ba8a 100644
--- a/html/asr.html
+++ b/html/asr.html
@@ -57,7 +57,7 @@ <h3 class="heading">IndicVoices 2.0</h3>
                     <h3 class="heading">Lahaja</h3>
                     <p>Lahaja is a benchmark featuring 12.5 hours of Hindi audio to facilitate a comprehensive assessment of Hindi ASR systems across various accents. This dataset includes read and spontaneous speech on diverse topics, collected from 132 speakers across 83 districts in India.</p>
                         <a href="https://github.com/AI4Bharat/Lahaja"><img src="../assets/logos/github.png"></a>
-                        <a href="arxiv"><img src="../assets/logos/paper.png"></a>
+                        <a href="https://arxiv.org/abs/2408.11440"><img src="../assets/logos/paper.png"></a>
                     <span class="date dataset">June 2024</span>
                     <span class="circle"></span>
                 </li>