HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

multitalker-parakeet-streaming-0.6b-v1

nvidia/multitalker-parakeet-streaming-0.6b-v1

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/multitalker-parakeet-streaming-0.6b-v1
provider
nvidia
license
other
language
—
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
677
likes
121
created
—
last modified
2026-01-28T02:03:41+00:00 (2026)
huggingface
https://huggingface.co/nvidia/multitalker-parakeet-streaming-0.6b-v1
tags
nemospeaker-diarizationspeech-recognitionmultitalker-ASRmultispeaker-ASRspeechaudioFastConformerRNNTConformerNESTpytorchNeMoautomatic-speech-recognitiondataset:AMIdataset:NOTSOFAR1dataset:Fisherdataset:MMLPCdataset:librispeech_train_clean_100dataset:librispeech_train_clean_360dataset:librispeech_train_other_500dataset:WSJdataset:SWBDdataset:europarl_dataset

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
WER AMIspeech-asr40.0**AMI SDM**medium| **AMI SDM** | 3-4 | 40 |
WER AMIspeech-asr21.26low| [Streaming Sortformer v2](https://huggingface.co/nvidia/diar_streaming_sortformer_4spk-v2) | 21.26 | 37.44 | 15.81 | 23.81 |
WER GigaSpeechspeech-asr11.45low| [Nemotron Speech Streaming ASR](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b) | 7.16 | 11.58 | 12.48 | 11.45 | 2.31 | 4.75 | 2.62 | 4.5 | 7.57 |
WER VoxPopulispeech-asr7.57low| [Nemotron Speech Streaming ASR](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b) | 7.16 | 11.58 | 12.48 | 11.45 | 2.31 | 4.75 | 2.62 | 4.5 | 7.57 |
WER TED-LIUMspeech-asr4.5low| [Nemotron Speech Streaming ASR](https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b) | 7.16 | 11.58 | 12.48 | 11.45 | 2.31 | 4.75 | 2.62 | 4.5 | 7.57 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.