Speech AI Tools

NeMo provides a set of tools useful for developing Automatic Speech Recognitions (ASR) and Text-to-Speech (TTS) synthesis models: NVIDIA/NeMo .

• NeMo Forced Aligner (NFA)
• Dataset Creation Tool Based on CTC-Segmentation
• Speech Data Explorer
• Comparison tool for ASR Models
• ASR Evaluator

There are also additional NeMo-related tools hosted in separate github repositories:

• Speech Data Processor
• (Inverse) Text Normalization