prakashsonti Goto Github PK

audio-metadata-updater

This Python script updates the metadata of WAV audio files, specifically the "Title" and "Track Number" fields, to match their file names (without the file extension).

fakeyou-tacotron2-notebook

Tacotron2 Training Notebook for FakeYou.com

rpi-object-detection

Real-time object detection and tracking using Raspberry Pi and OpenCV!

sfc-snowpark-environment

tacotron-2-audio-preprocessor

This Python script preprocesses audio files for training a Tacotron 2 text-to-speech model. It trims silence, normalizes the audio, and saves the processed files to a specified output folder. It's specifically designed to work with .wav files to help create a clean and consistent dataset for Tacotron 2 model training.

tacotron2-wav-file-renamer

A simple Python script to batch rename WAV files in a folder numerically, specifically designed to facilitate the management and organization of audio files generated by the Tacotron 2 text-to-speech system.

tacotron2-wav2vec-transcription

A Python script that uses the Wav2Vec2 model to transcribe .wav files and generates a .txt file for training a Tacotron2 text-to-speech model.

vehicle-count-detect