Skip to content

Instantly share code, notes, and snippets.

View AIAnytime's full-sized avatar
👋
On vacation

AI Anytime AIAnytime

👋
On vacation
View GitHub Profile
@AIAnytime
AIAnytime / top_p.text
Created October 30, 2023 08:09
top p top k thing
Nucleus sampling is a technique used in large language models to control the randomness and diversity of generated text. It works by sampling from only the most likely tokens in the model’s predicted distribution.
The key parameters are:
Temperature: Controls randomness, higher values increase diversity.
Top-p (nucleus): The cumulative probability cutoff for token selection. Lower values mean sampling from a smaller, more top-weighted nucleus.
Top-k: Sample from the k most likely next tokens at each step. Lower k focuses on higher probability tokens.
@AIAnytime
AIAnytime / deepfake_detection.py
Created May 27, 2023 14:43
Deepfake Audio Detection
import streamlit as st
import os
from tortoise.models.classifier import AudioMiniEncoderWithClassifierHead
from glob import glob
import io
import librosa
import plotly.express as px
import torch
import torch.nn.functional as F
import torchaudio
@AIAnytime
AIAnytime / stt.py
Created May 14, 2023 10:29
Speech to Text Assembly AI
# Assembly AI speech to text
def assemblyai_stt(audio_filename):
with open(audio_filename , "rb") as f:
response = requests.post(base_url + "/upload",
headers=headers,
data=f)
upload_url = response.json()["upload_url"]
data = {
"audio_url": upload_url
@AIAnytime
AIAnytime / pytube_audio.py
Created May 14, 2023 10:29
PyTube Audio Snippet
# PyTube function for YouTube video
def save_audio(url):
yt = YouTube(url)
video = yt.streams.filter(only_audio=True).first()
out_file = video.download()
base, ext = os.path.splitext(out_file)
file_name = base + '.mp3'
try:
os.rename(out_file, file_name)
except WindowsError:
@AIAnytime
AIAnytime / colorizer.py
Created April 16, 2023 08:21
Deoldify Images Streamlit
import streamlit as st
import fastai
from deoldify.visualize import *
def image_colorizer(url):
colorizer = get_image_colorizer(artistic=True)
source_url = url
render_factor = 35
watermarked = True
@AIAnytime
AIAnytime / reverse_sd.py
Created April 7, 2023 17:39
reverse_sd
# -*- coding: utf-8 -*-
"""Reverse SD.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1ci11cstH7uM9SPb6q2hb7f-IiZHYvcDq
"""
!pip install clip-interrogator==0.6.0
@AIAnytime
AIAnytime / spacy_streamlit_ner.py
Created February 18, 2023 16:12
Spacy Displacy Streamlit Code
HTML_WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem">{}</div>"""
@AIAnytime
AIAnytime / text_classifier_api.py
Created February 5, 2023 16:19
Text Classifier Fast API
from fastapi import FastAPI
import pickle
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
app = FastAPI()
# Load the Tfidf and Naive Bayes models
tfidf = pickle.load(open("tf_idf.pkt", "rb"))
@AIAnytime
AIAnytime / Toxicity_classifier.py
Created February 5, 2023 13:33
Toxicity Classifier
# -*- coding: utf-8 -*-
"""Toxicity Classifier NLP.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1UUZzQgrRUcLujGxbmhE30AlQALMsYXCm
"""
# Commented out IPython magic to ensure Python compatibility.
@AIAnytime
AIAnytime / noise_reduction
Created July 17, 2022 04:25
Noise is inevitably present in almost all acoustic environments. Even when recorded with a microphone, a speech signal will contain lots of noise, such as white noise or background sounds. Excessive noise can distort or mask the characteristics of s
import noisereduce as nr
from scipy.io import wavfile
# load data
rate, data = wavfile.read("voice_with_noise.wav")
# perform noise reduction
reduced_noise = nr.reduce_noise(y=data, sr=rate) It was originally published on https://www.apriorit.com/