DeepAI AI Chat
Log In Sign Up

Applying wav2vec2 for Speech Recognition on Bengali Common Voices Dataset

by   H. A. Z. Sameen Shahgir, et al.

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.


page 1

page 2

page 3

page 4


end-to-end training of a large vocabulary end-to-end speech recognition system

In this paper, we present an end-to-end training framework for building ...

ASR2K: Speech Recognition for Around 2000 Languages without Audio

Most recent speech recognition models rely on large supervised datasets,...

The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods

The variety of accents has posed a big challenge to speech recognition. ...

A Bag-of-Prototypes Representation for Dataset-Level Applications

This work investigates dataset vectorization for two dataset-level tasks...

Exploiting Context When Learning to Classify

This paper addresses the problem of classifying observations when featur...

A Comparison of Methods for OOV-word Recognition on a New Public Dataset

A common problem for automatic speech recognition systems is how to reco...

Visual Speech Language Models

Language models (LM) are very powerful in lipreading systems. Language m...