skip to content
gigarouter gigarouter
models / speech-to-text · coming soon

wav2vec2-xls-r-300m-bengali

arijitx/wav2vec2-xls-r-300m-bengali

A popular open speech-to-text model, with 1.4M downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.

status
coming soon
API providers
0
downloads / mo
1.4M
license
apache-2.0

about this model

Overview

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m for Bengali automatic speech recognition (ASR). It was trained on the OpenSLR SLR53 Bengali dataset and is hosted on gigarouter as a managed, OpenAI-compatible API. The model is optimized for transcribing Bengali speech with high accuracy, especially when combined with an external language model.

Performance

Evaluation was conducted on a held-out set of Bengali speech samples. The following word error rate (WER) and character error rate (CER) were achieved:

ConditionWERCER
Without language model0.21730.0473
With 5-gram language model (trained on 30M sentences from AI4Bharat IndicCorp)0.15320.0341
not yet live

We're benchmarking and onboarding wav2vec2-xls-r-300m-bengali as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.