Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call…
Nemotron 3.5 ASR Streaming Multilingual is an open 0.6B-parameter prompt-conditioned cache-aware FastConformer-RNNT model, engineered for low-latency streaming transcription across 40+ languages. It powers…
Nemotron-ASR-Streaming is a multi lingual, streaming Automatic Speech Recognition (ASR) engineered to deliver high-quality multi lingual transcription across both low-latency streaming and high-throughput…
Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic…
Audio reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts audio plus a prompt and returns text.
1B parameters · 25 languages · Encoder: Conformer-based · Decoder: Transformer
2.5B parameters · Encoder: Conformer-based · Decoder: Qwen2
0.64B parameters · 40 languages · Encoder: FastConformer (cache-aware) · Decoder: RNNT
0.62B parameters · Encoder: FastConformer (cache-aware) · Decoder: RNNT
1.1B parameters · Encoder: Conformer-based · Decoder: CTC
0.6B parameters · Encoder: Conformer-based · Decoder: TDT / RNN-T
0.6B parameters · Encoder: Conformer-based · Decoder: TDT
0.6B parameters · 26 languages · Encoder: Conformer-based · Decoder: TDT