Sponsored by
Vmake Labs Video Enhancer
-Vmake Labs Video Enhancer uses AI to improve video quality, restore details, reduce blur, and upscale videos to 8K.
Parakeet Ultra: Core ML encoder, GGUF decoder and full GGUF
Model files for
Parakeet Ultra
in
Glimpse
. Parakeet Ultra is Moondream's multilingual
fine-tune of NVIDIA Parakeet TDT 0.6B V3 (25 European languages, same architecture and size).
File
Download size
Use
parakeet-ultra-Q8_0-decoder.gguf
19.5 MB
Apple Silicon: predictor, joint network, tokenizer and metadata
parakeet-ultra-Q8_0-encoder-mf3.mlmodelc.zip
529 MB
Apple Silicon, macOS 15 or later: int8 Core ML encoder with 15 s, 10.24 s and 5.12 s functions
parakeet-ultra-Q8_0-encoder-macos14.mlmodelc.zip
524 MB
Apple Silicon, macOS 14: int8 Core ML encoder, one 15 s function
parakeet-ultra-Q8_0.gguf
740 MB
Windows, Intel Macs and any CPU/GPU path: full Q8_0 model
Apple Silicon downloads the decoder plus one encoder zip; other machines download the full GGUF.
Accuracy
Measured with Glimpse's engine on an M2 Pro (Neural Engine, int8 encoder), full test sets, against Parakeet TDT V3
in the same layout:
Parakeet TDT V3
Parakeet Ultra
FLEURS, 25 languages (8499 clips), WER
13.00%
10.77%
LibriSpeech test-clean / test-other, WER
2.19% / 4.03%
2.07% / 3.82%
554 s recording, transcription time
1.76 s
1.43 s
Every FLEURS language is better or the same. On Windows (RTX 4000 Ada, Vulkan, full GGUF) FLEURS WER is 12.53% vs
10.43%.
Provenance
Weights:
moondream/parakeet-ultra
(CC BY 4.0), based on
nvidia/parakeet-tdt-0.6b-v3
(CC BY 4.0). The safetensors were
repacked into V3's NeMo layout, converted with transcribe.cpp's
convert-parakeet.py
, quantized to Q8_0, and the
<unk>
token marked as a control token (the checkpoint emits it for characters missing from the vocabulary). The
decoder is extracted with
extract-parakeet-decoder.py
; the encoders are converted with per-channel int8 weights.
Extract either zip next to the decoder GGUF; both unpack to
parakeet-ultra-Q8_0-encoder.mlmodelc
, which
Glimpse-Speech pairs with the decoder by name. The files use the
tdt-0.6b-v3
variant profile and need
transcribe.cpp
at glimpse-hq main (ec5f294d or later) for
dictionary boosting of words the model spells differently. The predictor/joint decoder runs on the CPU.
Glimpse
These files power on-device dictation in
Glimpse
, a free, open-source dictation app for Mac
and Windows. The source is on
GitHub
.
Runs of Glimpse-Dictation Parakeet-Ultra-coreml on huggingface.co
67
Total runs
8
24-hour runs
22
3-day runs
56
7-day runs
67
30-day runs
More Information About Parakeet-Ultra-coreml huggingface.co Model
Parakeet-Ultra-coreml huggingface.co is an AI model on huggingface.co that provides Parakeet-Ultra-coreml's model effect (), which can be used instantly with this Glimpse-Dictation Parakeet-Ultra-coreml model. huggingface.co supports a free trial of the Parakeet-Ultra-coreml model, and also provides paid use of the Parakeet-Ultra-coreml. Support call Parakeet-Ultra-coreml model through api, including Node.js, Python, http.
Parakeet-Ultra-coreml huggingface.co is an online trial and call api platform, which integrates Parakeet-Ultra-coreml's modeling effects, including api services, and provides a free online trial of Parakeet-Ultra-coreml, you can try Parakeet-Ultra-coreml online for free by clicking the link below.
Glimpse-Dictation Parakeet-Ultra-coreml online free url in huggingface.co:
Parakeet-Ultra-coreml is an open source model from GitHub that offers a free installation service, and any user can find Parakeet-Ultra-coreml on GitHub to install. At the same time, huggingface.co provides the effect of Parakeet-Ultra-coreml install, users can directly use Parakeet-Ultra-coreml installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Parakeet-Ultra-coreml install url in huggingface.co: