The Decoder· Jonathan Kemper·· 5 h ago
Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition
AI summary
Nvidia has released Nemotron 3.5 Transcribe, an open speech recognition model that handles transcription, speaker recognition, and translation and takes its instructions as text prompts. It leads several benchmarks and uses only a sixth of the active parameters of its strongest open rival.
Selection record
Threshold 76Media and individualsFirst 71Second 76
Not admittedSum of both 147 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：英伟达发布开源语音识别模型及数据集
- Same event
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com