Python的音频工具

ADHD_Recognition with personal voice

The Morse Wave Translator software is an application designed to record audio signals and subsequently decode them into Morse code. The application leverages several Python libraries for this task, including PyQt5 for the creation of the graphical interface, sounddevice for audio recording, soundfile for reading and writing audio files, pygame ...

ses tanıma, ses analiz ve ses tespit projesidir. Projemizde giriş ifadesi olan sesin okunması, özniteliklerinin çıkarılması ve uygun dijital formata dönüştürülmesi adımları sırasıyla gerçekleştirilmiştir. Verilen ifadelerin yetersiz olması durumunda ses verisinin çoğaltılması ve kaliteli veriyi elde etme işlemleri uygulanmıştır.

Music player "based terminal/no GUI" scripted in python. Allow you to play and download music from youtube.

Voice Assistant powered by LangChain and OpenAI Whisper. Features real-time speech recognition, multi-LLM support (OpenAI, Google), and computer vision capabilities via OpenCV. Enables natural voice interactions with advanced AI responses.

Audio methods for pandas dataframes using soundfile

ADHD_Recognition with personal voice

Audio Imager & Editor Python Package

Python script that samples wav files you supply and then generates a meditation audio file.

Easy-to-use library for removing noise in voice recordings.

A Python-based application for real-time emotion detection from audio recordings, built with Streamlit and machine learning libraries.

An application that aims to produce the transcripts of a meeting. Apart from the transcripts, it incorporates an in-built Voice Classification Software, capable of identifying and distinguishing between each participant, thus personalizing the transcripts with respect to each participant

A scalable and non-invasive speech-based machine learning model for early Alzheimer's detection using mel-spectrograms and lightweight semi-supervised CNN with no transcription or neuroimaging needed.

we shall build a very simple speech recognition system that takes our voice as input and produces the corresponding text by hearing the input.

A Python-based digital audio signal filtering project using Butterworth low-pass filters. Loads a .wav file, applies noise reduction by filtering out high-frequency components, and visualizes the frequency response. Built with NumPy, SciPy, Matplotlib, and SoundFile.

BİL314-Sinyaller ve Sistemler Dersi/Final Projesi (Fourier Dönüşümü)

Telegram Bot that can: 1) Preprocess and save audio messages from dialogues to a SQLite DB, 2) Determine if there are faces on sent photos and store them in that case.

An automation script to create short videos from youtube. Perfect for creating short form content for Tiktok, Youtube and Twitter.