CASLLuaPythonR Language Model Action Set SyntaxDetailsExamples Examples Subsections: Deprecation Notice 24.1 Calculating Error Rates by Using Default Options 24.2 Calculating Error Rates with Specified ID and Text Column Names 24.3 Identifying Speakers 24.4 Identifying Speakers Using Pretrained Models 24.5 Identifying Speakers and Analyzing the Distance Column 24.6 Decoding RNN Scores 24.7 Decoding RNN Scores with Labels Specified 24.8 Importing a Language Model 24.9 Importing a Language Model with Mapping between Characters 24.10 Removing Redundant n-Grams and Merging Counts 24.11 Calculating Probabilities of n-Grams 24.12 Converting Text Data into n-Grams 24.13 Transcribing Speech 24.14 Transcribing Speech with GPUs 24.15 Transcribing Speech with a PyTorch Acoustic Model 24.16 Transcribing Speech with a PyTorch Acoustic Model and a PyTorch Speaker Model 24.17 End-to-End Speech to Text Using the transcribeSpeech Action 24.18 End-to-End Speech to Text with Speaker Identification Using the transcribeSpeech Action 24.19 End-to-End Speech to Text Using a Step-by-Step Approach 24.20 Training an RNN Acoustic Model 24.21 Training an n-Gram Language Model Last updated: March 12, 2026