Finish concatenate transcriptions script

Change transcription to fp16, and read if vocals separation is made into another script, if yes it doesn't separe vocals, if no it separe vocals

If twitch video has 1080p or 720p quality add 60 to quality string

transcribe with whisperx

Add pyannote.audio to requirements

Add whisperx to requirements

Manage files into transcribe.py

Into separe_vocals.py set modelscope and speechbrain methods

Add libraries for speechbrain to requirements

Add draft jupyter notebooks and audio_cacahe folder to gitignore

Script for translate concatenate transcription file and languajes list

Add libraries for translate into requirements.txt

Script for concatenate chunck transcriptions into one file

Set output transcription file as srt into transcrie.py

Add seconds of chuncks as input argument into slice_audio.py

Change name of separe.py to separe_vocals.py

Set slice_audio.py no verbose

Add notebook to study the wave form to separe well voices

Create script to transcript audios

Add whisper to requirements

Add json, srt, tsv, vrr to gitignore

Change output folder to vocals into separe.py

In slice_audio.py save output chunks files into a txt file

add txt to gitignore

Fix some bugs of separe.py

Slice audio in chunks

Download video and audio of youtube

Download video and audio of twitch

Add mp4 to gitignore

Update separe.py

Create script to separate voices into input audio file

Update requeriments

Update readme

Add to gitignore all scripts to puss and pull to github and huggingface

Create LICENSE

draft of separate audios

Update requeriments, add torch+cuda

Update requeriments, add torch+cuda

Update requeriments, add torch+cuda

First gradio interface

edit packages

edit requeriments and packages

add requirements.txt

Add packages.txt

First version of app, only hello world

update emogis of readme

initial commit