Parakeet vs Apple's Speech API vs MOSS: Benchmark Round 2
NVIDIA Parakeet TDT (CoreML) and MOSS-Transcribe-Diarize measured on the same 5,559 LibriSpeech utterances, same normalizer, and same scorer as our Apple SpeechAnalyzer benchmark, with raw transcripts released for independent rescoring.
评论
?
参与讨论