whatmodel.sh / stt / Multitalker Parakeet Streaming 0.6B v1
Multitalker Parakeet Streaming 0.6B v1
↗ share
+ contribute
Multitalker Parakeet Streaming 0.6B v1 is an open-weights speech-to-text model from NVIDIA, released October 2025. Licence: nvidia-open-model-license.
Catalogue identity notes
nvidia/multitalker-parakeet-streaming-0.6b-v1: streaming multi-speaker ASR built on Nemotron-Speech-Streaming with speaker kernels driven by diarization outputs (card). transcribe.cpp ships it as a bundle GGUF with the Sortformer diarizer; the catalog's params 739,989,513 count that bundle, so params_b is left out. Measured port pins upstream commit 8749fc7 (2026-01-28, current main). Repo created 2025-10-15.
Model information sources
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 Multitalker Parakeet Streaming 0.6B v1, out of 176 with a score, then more from NVIDIA.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 113 |  ESPnet WavLM Large + Conformer + Transformer LM | 50±4 | local | ||
| 114 | OWSM-CTC v3.1 1B | 50±4 | local | ||
| 115 | Multitalker Parakeet Streaming 0.6B v1 | 50±4 | local | ||
| 116 |  Omnilingual ASR CTC 1B v2 | 50±3 | local | ||
| 117 |  Whisper large (v1) | 49±2 | 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 | 2.2% ✎ | ▁···▁▁▂·▄▄██ beats 21/56 | 67% |
| FLEURS English test WER | 6.5% ✎ | ▁··▁▁▁▁▁▃▃█▁ beats 12/56 | 27% |
$ where to run it
Other ways to run it
- Run it as published · needs ~0.87 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/multitalker-parakeet-streaming-0.6b-v1-gguf bundle/multitalker-parakeet-streaming-0.6b-v1-Q8_0.gguf --local-dir models/multitalker-parakeet-streaming-0.6b-v1 && build/bin/transcribe-cli -m models/multitalker-parakeet-streaming-0.6b-v1/bundle/multitalker-parakeet-streaming-0.6b-v1-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 | = 49.8 |
$ 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