Welcome to SpeeQ’s documentation!

Welcome to the documentation for SpeeQ, a speech recognition framework for Python that is pronounced as “speekiu”. SpeeQ provides a powerful tool for developers and researchers to experiment with and train different speech recognition models quickly and easily. With SpeeQ, you can easily run various pre-implemented model architectures with just a few lines of code, making it an ideal choice for those who want to quickly prototype and test different speech recognition models.

Contents:

• Introduction
• Contribution
  • Change request
  • Bug Report
  • Feature request
  • License
• Tutorials
  • Framework structure
  • Components
    • Config
    • Data
    • Models
    • Predictors
    • Trainers
    • Utils
  • Data Preperation
  • Train your first model
    • Model Building
    • Setting up data pipelines
    • Defining Speech and Text processor
      • Text Processor
      • Speech Processor
    • Building ASRDataConfig
    • Training
  • Prediction

Modules:

• Data
  • Augmenters
  • Data Loaders
  • Padders
  • Data Processes
  • Processors
  • Registry
  • Tokenizers
• Models
  • Activations
  • CTC Models
  • Decoders
  • Encoders
  • Layers
  • Registry
  • Seq2Seq Models
  • Skeletons
  • Model Templates
  • Transducer Models
• Configs
  • ASRDataConfig
  • DistConfig
  • ModelConfig
  • TrainerConfig
• Trainers
  • Criterions
  • Registry
  • Schedulers
  • Templates
  • Trainers
• Utils
  • Loggers
  • Utils
• Predictors
  • CTCPredictor
  • Seq2SeqPredictor
  • TransducerPredictor

Links:

• Github