Created an ASR (Automatic Speech Recognition) system that takes in individual recordings. Each recording represents a sentence composed of 5-10 English language digits, separated by adequate pauses. The system involves segmenting the sentence using a classifier, differentiating between background and foreground sounds.

Interface for automated transcription and time alignment of conversational interview data

Whisper realtime streaming for long speech-to-text transcription and translation.

An ASR Gradio GUI based project that transcript the audion and provides NLP based analysis.

Functionality for speech data processing including time alignment, encoding with speech encoders (tokenizers) and data preprocessing of common datasets

Prototype of an intelligent research agent capable of literature retrieval, summarization, and contextual reasoning — a foundation for scientific automation tools.

This project presents Hera, an Operating System level voice recognition package that understands voice commands to perform actions to simplify the user’s workflow. We propose a modernistic way of interacting with Linux systems, where the latency of conventional physical inputs are minimized through the use of natural language speech recognition.

ASR telegram assistant for voice/video messages transcribing

A powerful web-based editor for transcription and subtitle files with real-time audio/video sync capabilities

Metric evaluator for Automatic Speech Recognition using the HATS dataset

api for speach recognithion with gigaam model

Quick eval to try answer a question: how much does speaking pace affect WER/accuracy in ASR?

Tensorflow implement of LAS model

Generate transcript for Google ASR json files

Forced alignment decoder for Whisper.

Huggingface로 구현한 Transformer-Transducer

ScrAIbe Assistant is designed to leverage Whisper for precise audio processing and local LLMs via Ollama for efficient summarization. This tool is perfect for tasks such as taking notes from team meetings or lectures, offering a secure environment where no data—be it text, audio, or otherwise—leaves your local machine.

This project involves building a gradio website that accepts user audio input. It then transcribes the audio into Persian text and analyzes the speech to label its sentiment as positive or negative.

mocoVoice MCP Server

Real-time audio transcription monitoring system with AI-powered note generation using DeepSeek API