HF Model & Benchmark Matrix

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

parakeet-tdt-0.6b-v2-gguf

handy-computer/parakeet-tdt-0.6b-v2-gguf

kind
gguf
quant
gguf (16-bit)
family
misc
modality
automatic-speech-recognition
root model
nvidia/parakeet-tdt-0.6b-v2
provider
handy-computer
license
cc-by-4.0
language
en
context
—
library
transcribe.cpp
vRAM (GB)
—
size on disk
—
downloads
123,024
likes
0
created
—
last modified
2026-06-28T13:15:58+00:00 (2026)
huggingface
https://huggingface.co/handy-computer/parakeet-tdt-0.6b-v2-gguf
tags
transcribe.cppggufasrspeech-to-textparakeetconformerrnnttdtautomatic-speech-recognitionenarxiv:2305.05084arxiv:2304.06795arxiv:2406.00899arxiv:2410.01036arxiv:2505.13404base_model:nvidia/parakeet-tdt-0.6b-v2base_model:quantized:nvidia/parakeet-tdt-0.6b-v2license:cc-by-4.0region:us

Benchmark scores (7)

benchmarkcategoryscorecontextconfevidence
WER AMIspeech-asr11.16high| parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - |
WER Earnings-22speech-asr11.15high| parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - |
WER GigaSpeechspeech-asr9.74high| parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - |
WERspeech-asr6.05high| parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - |
WER VoxPopulispeech-asr5.95high| parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - |
WER TED-LIUMspeech-asr3.38high| parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - |
WER SPGISpeechspeech-asr2.17high| parakeet-tdt-0.6b-v2 | 6.05 | 11.16 | 11.15 | 9.74 | 1.69 | 3.19 | 2.17 | 3.38 | 5.95 | - |

Discussions (0)

none scraped.

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