nvidia/nemotron-speech-streaming-en-0.6b

Add NeMo-Speech.cpp GGUF (#21)

Update README: available in Transformers 5.13.0 (#20)

docs(readme): add 🤗 Transformers usage + transformers/hf-asr-leaderboard tags (#19)

Add 🤗 Transformers support (#17)

Add link to nemotron-3.5-asr-streaming-0.6b

docs(readme): add NIM Try via API (Nemotron ASR Streaming) (#16)

update NIM checkpoint

update the model checkpoint

update the results figure

Update model card with new model checkpoint March 13 2026 and results

Add links to Multitalker Parakeet Streaming and Parakeet Realtime EOU

update link to pipecat repo

fix typo in model card

add wer_scaling figure to readme

Upload results_wer_and_scaling.png

update tags

Update README.md

update model card based on feedback

update model card based on feedback

Updated model card based on feedback

Added links to HF blog, HF space, Modal endpoint, and Pipecat voicebot implementation

upload nemotron-speech-streaming-en-0.6b.nemo checkpoint

Delete nemotron-speech-streaming-en-0.6b.nemo

added pipeline inference code

add description of streaming inference pipeline (#1)

added bais, explainability, privacy, safety model cards

Added DGX spark after testing

update model card

corrected model name

improved UI components

updated model card

updated model name, table beautification

Rename nemotron-speech-realtime-en-600m.nemo to nemotron-speech-streaming-en-0.6b.nemo

Update the inference script parameters

added results for 80msec

upload figures for model card

Delete figures/caching_schema.png

add figures for model card

upload figures for model card

Upload nemotron-speech-realtime-en-600m.nemo

updated model card fixing reference to google speech commands dataset

added nemotron-speech-realtime-en-600m model card

initial commit