bigsnarfdude

# All model tests
bundle exec rspec spec/models/

# All controller tests  
bundle exec rspec spec/controllers/

# All request tests
bundle exec rspec spec/requests/

# All feature tests

bigsnarfdude

pip install outline-wiki-api
import os
os.environ["OUTLINE_API_KEY"] = "your_api_key"
os.environ["OUTLINE_INSTANCE_URL"] = "your_instance_url"
from outline_wiki_api import OutlineClient
client = OutlineClient(api_key=os.environ["OUTLINE_API_KEY"], server_url=os.environ["OUTLINE_INSTANCE_URL"])
collection_id = "your_collection_id"
new_document = client.documents.create(title="My Document", collection_id=collection_id, text="Content of my document")

bigsnarfdude

#!/usr/bin/env python3

"""
MP4 to MP3 Converter with MLX Parakeet Transcription (Threaded)
--------------------------------------------------
This script processes MP4 files from a CSV file using multiple threads with a staged pipeline approach:
1. Reads a CSV file with video information
2. Downloads MP4 files if needed
3. Converts MP4 files to MP3
4. Generates transcripts using MLX Parakeet

bigsnarfdude

#!/usr/bin/env python3

"""
MP4 Download Service
-------------------
This script handles only the downloading aspect of the MP4 processing pipeline:
1. Reads a CSV file with video information
2. Downloads MP4 files up to a configurable disk space limit
3. Maintains a queue of pending downloads
4. Provides robust resumption capability

bigsnarfdude

#!/usr/bin/env python3

"""
Multi-Process MP4 to MP3 Converter with Transcription
-----------------------------------------------------
This script processes MP4 files from a CSV file using multiple parallel processes:
1. Reads a CSV file with video information
2. Divides the work among multiple processes
3. Each process handles downloading, converting, and transcribing its assigned videos
4. Maintains robust resumption capability for each process

bigsnarfdude

from nemo.collections.asr import models as nemo_asr
import numpy as np
import librosa
import soundfile as sf
import os

def transcribe_with_chunking(audio_path, asr_model, chunk_duration=30, overlap_duration=2):
    """
    Transcribe audio file by breaking it into overlapping chunks
    

bigsnarfdude

import requests
from bs4 import BeautifulSoup
import csv
import time
import re
from urllib.parse import urljoin

def fetch_page(url, max_retries=3, retry_delay=2):
    """Fetch a page with retry logic and return BeautifulSoup object"""
    headers = {

bigsnarfdude

#!/usr/bin/env python3

"""
Video Processing Script

This script processes a list of video files from a CSV file:
1. Downloads the MP4 videos from URLs
2. Converts the videos to MP3 format
3. Generates transcripts from the MP3 files
4. Stores files in appropriate folders

bigsnarfdude

Steps to Set Up BIRS Workshops with Docker

1. Clone the repository (if you haven't already):

   git clone https://github.com/birs-math/workshops.git
   cd workshops

2. Copy the example configuration files to create your actual configuration files:

bigsnarfdude

from parakeet_mlx import from_pretrained
import numpy as np
import librosa
import soundfile as sf
import os

def transcribe_with_chunking(audio_path, model, chunk_duration=30, overlap_duration=2):
    """
    Transcribe audio file by breaking it into overlapping chunks