Hugging Face's logo

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

Automatic Speech Recognition
NeMo
PyTorch
speaker-diarization
speech-recognition
multitalker-ASR
multispeaker-ASR
speech
audio
FastConformer
RNNT
Conformer
NEST
NeMo
Eval Results (legacy)
Model card Files
xet
 Community
3

Multilingual model planned?

#2
by fosple - opened
Discussion
fosple

Thanks for sharing! This is a really nice model - thanks for all the work which went into it ❤️

Is there a multilingual version planned (like parakeet-tdt-0.6b-v3)? I'm particularity interested in German, Spanish, Italian & French.

Best
fosple
taejinp
 NVIDIA org

Hi.
We will be looking into non-English ASR support in the near future.
Note that Sortformer speaker diarization model is not limited to English.
Only multitalker Parakeet ASR model is limited to English.

fosple
•
edited Dec 7, 2025

@taejinp Thanks for the info :) Do you know if a "parakeet-streaming-0.6b" model (w/o speaker diarization) is planned? So like nvidia/parakeet-tdt-0.6b-v3 but optimized for streaming?
Amargolin
 NVIDIA org

Try this : https://huggingface.co/nvidia/parakeet_realtime_eou_120m-v1
Aleks123456

so basically if one instance of this model accepts audio of 2 speakers, whoever speaks first will be transcribed only till the end of audio?

Sign up or log in to comment