Transcript Tagger

A comprehensive toolkit for tagging and analyzing transcript content using AI. This SDK allows you to automatically categorize and determine the difficulty level of transcript text.

Features

• AI-Powered Content Tagging: Generate relevant topic, format, audience, and other tags for transcript content
• Content Difficulty Analysis: Analyze and rate the difficulty level of transcript content based on various metrics
• Fully Customizable: Configure thresholds, categories, and storage options to fit your needs
• Command Line Interface: Process transcripts directly from the command line
• Python API: Integrate tagging and analysis capabilities into your own applications

Installation

pip install transcript-tagger

Quick Start

Basic Usage

from transcript_tagger_sdk import TranscriptTagger, Config

# Create a tagger with default configuration
config = Config()
config.set_api_key("your-openai-api-key")
config.set_model("gpt-4")
config.set_storage_path("./custom/path")

tagger = TranscriptTagger(config)

# Process a transcript file
result = tagger.process_transcript("path/to/transcript.txt")

# Access the results
print(f"Difficulty level: {result['difficulty']['difficulty_name']}")
print(f"Topics: {result['tags'].get('Topic', [])}")

Analyzing Difficulty Only

from transcript_tagger_sdk import DifficultyAnalyzer

config = Config()
config.set_api_key("your-openai-api-key")
config.set_model("gpt-4")
config.set_storage_path("./custom/path")

# Create an analyzer
analyzer = DifficultyAnalyzer(config)

# Analyze text
result = analyzer.analyze_text("Your transcript text here...")

# Print difficulty level
print(f"Difficulty: {result['difficulty_name']} ({result['difficulty_level']}/5)")

Custom Configuration

from transcript_tagger_sdk import Config, TranscriptTagger

# Create custom configuration
config = Config()
config.set_api_key("your-openai-api-key")
config.set_model("gpt-4")
config.set_storage_path("./custom/path")

# Custom readability thresholds
config.set_readability_thresholds({
    "Beginner": 3.0,  # 0-3.0
    "Intermediate": 9.0,  # 3.1-9.0
    "Advanced": 15.0,  # 9.1+
})

# Create tagger with custom config
tagger = TranscriptTagger(config)

Command Line Usage

Process transcripts:

# Process a single transcript
transcript-tagger process path/to/transcript.txt

# Process multiple transcripts
transcript-tagger process file1.txt file2.txt file3.txt

# Only analyze difficulty (no tagging)
transcript-tagger process --difficulty-only transcript.txt

# Only generate tags (no difficulty analysis)
transcript-tagger process --tags-only transcript.txt

View results:

# View all results
transcript-tagger view

# View results for a specific video ID
transcript-tagger view --video-id video123

Advanced Usage

For more advanced usage examples, check out the examples directory:

• basic_usage.py: Simple usage example
• advanced_usage.py: Advanced features including batch processing and custom configurations

API Reference

Main Classes

• TranscriptTagger: Main class for tagging and analyzing transcripts
• Config: Configuration class for customizing tagger behavior
• DifficultyAnalyzer: Class for analyzing the difficulty level of text

Difficulty Levels

The toolkit defines 5 difficulty levels:

1. 初级/Beginner: Basic vocabulary, simple sentences, suitable for beginners
2. 初中级/Elementary: Slightly more complex vocabulary, suitable for early learners
3. 中级/Intermediate: Moderate complexity, suitable for intermediate learners
4. 中高级/Upper-Intermediate: More complex language, suitable for advanced learners
5. 高级/Advanced: Complex vocabulary and sentence structures, suitable for proficient users

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.