HF Model & Benchmark Matrix

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

parakeet-tdt-0.6b-EN-Medical

yuriyvnv/parakeet-tdt-0.6b-EN-Medical

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/parakeet-tdt-0.6b-v3
provider
yuriyvnv
license
cc-by-4.0
language
en
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
9,326
likes
0
created
—
last modified
2026-06-03T10:30:39+00:00 (2026)
huggingface
https://huggingface.co/yuriyvnv/parakeet-tdt-0.6b-EN-Medical
tags
nemoautomatic-speech-recognitionspeechparakeetfastconformertdtenglishnvidiamedicalmultimedcommon-voicefine-tunedendataset:leduckhai/MultiMeddataset:fixie-ai/common_voice_17_0base_model:nvidia/parakeet-tdt-0.6b-v3base_model:finetune:nvidia/parakeet-tdt-0.6b-v3license:cc-by-4.0model-indexregion:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr22.84mediumWER 22.84%
WERspeech-asr19.22Zero-shot WER | Zero-shot CERlow| 🩺 MultiMed English (test) | 7,567 | 19.22 | **14.31** | **-4.91** (-25.5%) | 14.16 | **10.37** |
WER Common Voicespeech-asr17.0mediumCommon Voice 17
CERspeech-asr14.16Zero-shot WER | Zero-shot CERlow| 🩺 MultiMed English (test) | 7,567 | 19.22 | **14.31** | **-4.91** (-25.5%) | 14.16 | **10.37** |
WER Common Voicespeech-asr8.58🗣️ Common Voice 17 EN (test)medium| 🗣️ Common Voice 17 EN (test) | 16,393 | 8.58 | **9.11** | **+0.53** (+6.2%) | 4.01 | **4.10** |

Discussions (0)

none scraped.

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