# Applying wav2vec2 for Speech Recognition on Bengali Common Voices Dataset

arXiv: https://arxiv.org/abs/2209.06581 · HTML: https://mlsanity.com/paper/2209.06581/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 11 Sep 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [Low-resource Languages: A Review of Past Work and Future Challenges](https://mlsanity.com/paper/2006.07264/) (2020)
- [Simple and Effective Zero-shot Cross-lingual Phoneme Recognition](https://mlsanity.com/paper/2109.11680/) (2021)
- [Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages](https://mlsanity.com/paper/2012.12121/) (2020)
- [Bengali Common Voice Speech Dataset for Automatic Speech Recognition](https://mlsanity.com/paper/2206.14053/) (2022)

## Built on by (most cited first, 4 of 4)

- [OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking](https://mlsanity.com/paper/2305.09688/) (2023)
- [End to end Hindi to English speech conversion using Bark, mBART and a finetuned XLSR Wav2Vec2](https://mlsanity.com/paper/2401.06183/) (2024)
- [Investigating self-supervised, weakly supervised and fully supervised training approaches for multi-domain automatic speech recognition: a study on Bangladeshi Bangla](https://mlsanity.com/paper/2210.12921/) (2022)
- [Transcription and translation of videos using fine-tuned XLSR Wav2Vec2 on custom dataset and mBART](https://mlsanity.com/paper/2403.00212/) (2024)

## Abstract (arXiv)

Speech is inherently continuous, where discrete words, phonemes and other units are not clearly segmented, and so speech recognition has been an active research problem for decades. In this work we have fine-tuned wav2vec 2.0 to recognize and transcribe Bengali speech -- training it on the Bengali Common Voice Speech Dataset. After training for 71 epochs, on a training set consisting of 36919 mp3 files, we achieved a training loss of 0.3172 and WER of 0.2524 on a validation set of size 7,747. Using a 5-gram language model, the Levenshtein Distance was 2.6446 on a test set of size 7,747. Then the training set and validation set were combined, shuffled and split into 85-15 ratio. Training for 7 more epochs on this combined dataset yielded an improved Levenshtein Distance of 2.60753 on the test set. Our model was the best performing one, achieving a Levenshtein Distance of 6.234 on a hidden dataset, which was 1.1049 units lower than other competing submissions.