# Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla

arXiv: https://arxiv.org/abs/2507.01931 · HTML: https://mlsanity.com/paper/2507.01931/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers](https://mlsanity.com/paper/2307.03183/) (2023)
- [A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition](https://mlsanity.com/paper/2204.05419/) (2022)
- [Modular Domain Adaptation for Conformer-Based Streaming ASR](https://mlsanity.com/paper/2305.13408/) (2023)
- [Model Adaptation for ASR in low-resource Indian Languages](https://mlsanity.com/paper/2307.07948/) (2023)

## Built on by (most cited first, 6 of 6)

- [BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects](https://mlsanity.com/paper/2510.06188/) (2025)
- [LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families](https://mlsanity.com/paper/2603.20042/) (2026)
- [grapheme-kit: Grapheme-Level Metrics and Text Processing for Multilingual NLP](https://mlsanity.com/paper/2607.22456/) (2026)
- [BanglaRobustNet: A Hybrid Denoising-Attention Architecture for Robust Bangla Speech Recognition](https://mlsanity.com/paper/2601.17679/) (2026)
- [When Surveys Become Conversations: Adaptive Matrix Validation for AI-Assisted Interviews](https://mlsanity.com/paper/2606.24244/) (2026)
- [Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages](https://mlsanity.com/paper/2609.29798/) (2026)

## Abstract (arXiv)

In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech Recognition (ASR) models, OpenAI's Whisper (Small & Large-V2) and Facebook's Wav2Vec-BERT on Bangla, a low-resource language. We have conducted experiments using two publicly available datasets: Mozilla Common Voice-17 and OpenSLR to evaluate model performances. Through systematic fine-tuning and hyperparameter optimization, including learning rate, epochs, and model checkpoint selection, we have compared the models based on Word Error Rate (WER), Character Error Rate (CER), Training Time, and Computational Efficiency. The Wav2Vec-BERT model outperformed Whisper across all key evaluation metrics, demonstrated superior performance while requiring fewer computational resources, and offered valuable insights to develop robust speech recognition systems in low-resource linguistic settings.