Open ASR Leaderboard
Explore speech model benchmarks across languages and datasets
None defined yet.
Explore speech model benchmarks across languages and datasets
Evaluate text normalization accuracy on your data
Normalize raw text into clean, readable format
Run model evaluation with builtβin data normalizer
Evaluate speech transcription and speaker diarization results
Evaluate text normalizer performance on your data
Generate AIβcrafted music from text prompts
Run batch question answering evaluation locally
Run evaluations on chat model responses
Run evaluation of chat model responses
Run model evaluation and get performance metrics
Evaluate text normalizers and get performance metrics
Normalize text for consistent formatting and clean data
Normalize text data and evaluate its quality
Normalize text to a consistent, clean format
Normalize and clean text data for analysis
Normalize and evaluate your text data
Normalize your text quickly and consistently
Evaluate speculative decoding performance for language models
Evaluate nonβautoregressive text generation models
Transcribe audio or YouTube videos to text
Transcribe audio or YouTube videos into text