parakeet-tdt-ctc-110m-coreml

Home/Models/FluidInference/parakeet-tdt-ctc-110m-coreml

FluidInference/parakeet-tdt-ctc-110m-coreml

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: nvidia/parakeet-tdt_ctc-110m
provider: FluidInference
license: cc-by-4.0
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 1,023
likes: 0
created: —
last modified: 2026-03-16T22:37:03+00:00 (2026)
huggingface: https://huggingface.co/FluidInference/parakeet-tdt-ctc-110m-coreml
tags: coremlhybrid_tdt_ctcautomatic-speech-recognitionspeechaudioTransducerTDTFastConformerConformerpytorchNeMohf-asr-leaderboardenarxiv:2305.05084arxiv:2304.06795base_model:nvidia/parakeet-tdt_ctc-110mbase_model:quantized:nvidia/parakeet-tdt_ctc-110mlicense:cc-by-4.0region:us

benchmark	category	score	context	conf	evidence
WER AMI	speech-asr	15.88	AMI	medium	`\| AMI \| 15.88% \|`
WER Earnings-22	speech-asr	12.42	Earnings-22	medium	`\| Earnings-22 \| 12.42% \|`
WER GigaSpeech	speech-asr	10.52	GigaSpeech	medium	`\| GigaSpeech \| 10.52% \|`
WER LibriSpeech	speech-asr	5.2	LibriSpeech test-other	medium	`\| LibriSpeech test-other \| 5.2% \|`
WER TED-LIUM	speech-asr	4.16	TEDLIUM-v3	medium	`\| TEDLIUM-v3 \| 4.16% \|`
WER	speech-asr	3.0		low	`\| LibriSpeech test-clean \| 3.0% \|`
WER LibriSpeech	speech-asr	3.0	LibriSpeech test-clean	medium	`\| LibriSpeech test-clean \| 3.0% \|`

none scraped.