visualization-t-sne-clustering-pca-speech

vits-tts-positional-phoneme-codebase

voc_xml_to_csv

voc_xml_to_json_on_dhaka_ai_dataset

vocoders_tts

voice-assistant-chatgpt

Voice Assistant based on Whisper ASR and ChatGPT API

voice_conversion_embedding_of_spkrec_xvect_voxceleb_speecht5

weighted-boxes-fusion

Set of methods to ensemble boxes from object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

whisper_asr_with_augmentations

whisper_bangla_pre_pro_gpu

whisper_hinge_embedding_loss_poc

whisper_layer_pruning

whisper_logit_lens

This Alignment Jam Hackathon project explores whether the concept of "logit lens" applies to the encoder and decoder layers in Whisper, an end-to-end speech recognition model.

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers

yolo-v5-version-of-dhaka-ai

Dhaka-AI

yolov3-solution-of-dhaka-ai

youtube-audio-transcriber-summarizer

Youtube-Audio-Transcriber/Summarizer is a Python script that extracts audio from YouTube videos, transcribes it using OpenAI's Whisper ASR API, and summarizes the content with OpenAI's GPT-3 API, providing concise insights from video content for quick understanding and analysis.