Authors

Venue

Date

Share

Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization

Pankaj Wasnik

Kumud Tripathi

Raj Gothi

ICASSP-25

2025

Abstract

Automatic speech recognition has recently seen a significant advancement with large foundational models such as Whisper. However, these models often struggle to perform well in low-resource languages, such as Indian languages. This paper explores two novel approaches to enhance Whisper's multilingual speech recognition performance in Indian languages. First, we propose prompt-tuning with language family information, which enhances Whisper's accuracy in linguistically similar languages. Second, we introduce a novel tokenizer that reduces the number of generated tokens, thereby accelerating Whisper's inference speed. Our extensive experiments demonstrate that the tokenizer significantly reduces inference time, while prompt-tuning enhances accuracy across various Whisper model sizes, including Small, Medium, and Large. Together, these techniques achieve a balance between optimal WER and inference speed.

Related Publications

Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection

CVPRW, 2025
Ayush Ghadiya, Purbayan Kar, Vishal Chudasama, Pankaj Wasnik

Recently, weakly supervised video anomaly detection (WS-VAD) has emerged as a contemporary research direction to identify anomaly events like violence and nudity in videos using only video-level labels. However, this task has substantial challenges, including addressing imba…

Open-Set Object Detection By Aligning Known Class Representations

WACV, 2025
Vishal Chudasama, Naoyuki Onoe*, Pankaj Wasnik, Hiran Sarkar, Vineeth N Balasubramanian

Open-Set Object Detection (OSOD) has emerged as a contemporary research direction to address the detection of unknown objects. Recently, few works have achieved remarkable performance in the OSOD task by employing contrastive clustering to separate unknown classes. In contra…

EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion

AAAI, 2025
Ashishkumar Gudmalwar, Nirmesh Shah*, Pankaj Wasnik, Ishan Biyani, Rajiv R. Shah

The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion intensity in the diffusion-based EVC frame…

  • HOME
  • Publications
  • Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.