text2speech

A collection of tools, datasets and resources on Bangla computing

BNLP is a natural language processing toolkit for Bengali Language.

This repository contains the official release of the model "BanglaBERT" and associated downstream finetuning code and datasets introduced in the paper titled "BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla" accpeted in Findings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: NAACL-2022.

Bangla NLP dataset. Bangla NER,POStag, text summarization, stopword, translate, sentiment analysis, wiki articles, root word, dataset etc.

Fully Configurable RAG Pipeline for Bengali Language RAG Applications. Supports both Local and Huggingface Models, Built with Langchain.

Machine Translation using Transfromers

MediBeng Whisper Tiny 通过训练 Whisper Tiny 模型来翻译孟加拉语和英语混合语音，将其转换成英语，从而改进医生与患者对话的转录工作。这使得分析、记录保存以及在医疗保健中使用人工智能变得更加容易。

BanglaTTS is a text-to-speech (TTS) system for Bangla language that works in offline mode. You can convert text to speech in male or female voice.

Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network

Fine tuned llama 3 models for context based question answering in bengali language.