Pinned Loading

1. BanglaASR BanglaASR Public

   Bangla ASR using Fast Conformer CTC (NVIDIA NeMo). This repository contains a Bangla Automatic Speech Recognition (ASR) model built using NVIDIA's NeMo framework and Fast Conformer architecture wit…

   Jupyter Notebook 2

2. BanglaTTS BanglaTTS Public

   Bangla TTS using VITS and Coqui-ai Toolkit. This repository contains a Bangla Text-to-Speech (TTS) system trained on mono (male) speakers using the ViT-TTS model from the paper "ViT-TTS: Visual Tex…

   Python 1

3. Bangla-Image-Caption-Generation Bangla-Image-Caption-Generation Public

   The Bangla Image Caption Generation system generates descriptive captions for images in the Bangla language. The model is built by translating English captions from the Flickr8k dataset into Bangla…

   Python 3

4. OOTDiffusion OOTDiffusion Public

   Forked from levihsu/OOTDiffusion

   Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

   Python 1

5. agentic_patterns agentic_patterns Public

   Forked from neural-maze/agentic_patterns

   Implementing the 4 agentic patterns from scratch

   Jupyter Notebook

6. parler-tts parler-tts Public

   Forked from huggingface/parler-tts

   Inference and training library for high-quality TTS models.

   Python