whatmodel.sh / stt / Nemotron Speech Streaming EN 0.6B
Nemotron Speech Streaming EN 0.6B
↗ share
+ contribute
Nemotron Speech Streaming EN 0.6B is an open-weights speech-to-text model from NVIDIA, released March 2026. Its published size is 0.618B parameters. Licence: nvidia-open-model-license.
Catalogue identity notes
nvidia/nemotron-speech-streaming-en-0.6b main-branch checkpoint (card: 'March 12, 2026: nemotron-asr-streaming was released with updated checkpoint (trained on larger corpora). For the older checkpoint released in January 2026, please refer to the nemotron-speech-streaming-jan2026 branch'). English cache-aware FastConformer-RNNT, 600M per card. transcribe.cpp port of main at ef3bf40 (2026-05-03); later commits add Transformers support, a link and a NeMo-Speech.cpp GGUF, not new weights per their titles. Not the multilingual nemotron-3-5-asr-streaming-0-6b (catalogued). released = March 2026 checkpoint update; repo created 2025-12-17.
Model information sources
Release date ↗ · Parameter count ↗
Hugging Face safetensors metadata total 618,084,865 (current main ebe59e5); transcribe.cpp catalog counts 618,079,745 for the converted port.
Score within the Open ASR English short-form WER (March 2026) comparison set only.
$ how it compares
The speech-to-text models ranked either side of Nemotron Speech Streaming EN 0.6B, out of 176 with a score, then more from NVIDIA.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 117 |  Whisper large (v1) | 49±2 | local | ||
| 118 |  OWSM-CTC v3.2 ft 1B | 49±4 | local | ||
| 119 | Nemotron Speech Streaming EN 0.6B | 49±4 | local | ||
| 120 |  Ultravox v0.6 (Llama 3.1 8B) | 49±5 | comparison only | ||
| 121 | Whisper medium.en | 48±3 | local | ||
| more from NVIDIA | |||||
| 28 | Canary-Qwen-2.5B | 61±2 | local | ||
| 35 | Parakeet TDT 0.6B v2 | 60±1 | local | ||
| 37 | Parakeet Unified EN 0.6B | 60±4 | local | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
other tests2 not in a task · 94% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LibriSpeech test-clean WER | 2.3% ✎ | ▁···▁▁▂·▄▄██ beats 18/56 | 67% |
| FLEURS English test WER | 6.4% ✎ | ▁··▁▁▁▁▁▃▃█▁ beats 14/56 | 27% |
$ where to run it
Other ways to run it
- Run it as published · needs ~0.73 GB · from github.com/handy-computer
git clone https://github.com/handy-computer/transcribe.cpp.git && cd transcribe.cpp && cmake -B build && cmake --build build && hf download handy-computer/nemotron-speech-streaming-en-0.6b-gguf nemotron-speech-streaming-en-0.6b-Q8_0.gguf --local-dir models/nemotron-speech-streaming-en-0.6b && build/bin/transcribe-cli -m models/nemotron-speech-streaming-en-0.6b/nemotron-speech-streaming-en-0.6b-Q8_0.gguf audio.wav
Official weights and documentation: huggingface.co/nvidia ↗
$ how the score was worked out · transcribe.cpp model catalog… 94%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports | 2 | 94% |
| prior · pull toward the middle | 6% | |
| weighted average | = 48.8 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json