Downloads · 30 days
466
100% of all-time downloads
parakeet-ultra-coreml
FluidInference/parakeet-ultra-coreml
parakeet-ultra-coreml is a automatic speech recognition model from FluidInference. Use it when you need speech turned into text. It is set up for fluidaudio. The card lists the license as cc-by-4.0.
Core ML build of moondream/parakeet-ultra, a full-precision post-training of nvidia/parakeet-tdt-0.6b-v3. Same architecture, 25 languages, tokenizer and output conventions as v3; drop-in for the v3 component contract.…
All-time downloads
466
Public
Repo size
631 MB
Likes
4
Trending 4
Repo makeup
Click a slice to open those files.
.bin631 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- fluidaudio
- License
- cc-by-4.0
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026
- SHA
- 95eaa59a
Base models
Model card
From the Hugging Face model README
parakeet-ultra-coreml
Core ML build of moondream/parakeet-ultra, a full-precision
post-training of nvidia/parakeet-tdt-0.6b-v3. Same architecture, 25 languages, tokenizer and output conventions as
v3; drop-in for the v3 component contract. Encoder is int8 linear per-channel (595 MB); decoder and joint are
re-exported from the Ultra checkpoint; preprocessor and vocabulary are the v3 ones.
Usage (FluidAudio ≥ next release)
let models = try await AsrModels.downloadAndLoad(version: .ultra)
let asr = AsrManager()
try await asr.initialize(models: models)
let result = try await asr.transcribe(audioFileURL)
swift run fluidaudiocli transcribe audio.wav --model-version ultra
Accuracy (FluidAudio, M-series Mac, full corpora, corpus-level WER)
| v3 (Core ML) | ultra (this repo) | |
|---|---|---|
| LibriSpeech test-clean (2620 files) | 2.27 % | 2.13 % |
| LibriSpeech test-other (2939 files) | 4.12 % | 3.81 % |
| FLEURS, 24 languages × 100 samples, mean | 14.81 % | 11.67 % |
Ultra wins all 24 FLEURS languages. The int8 encoder scores the same WER as an fp16 export (2.13 % / 3.79 %). Speed is within a few percent of v3 run back to back on the same machine (test-clean 126.7× vs 128.6× on the ANE).
Files
| File | Notes |
|---|---|
Encoder.mlmodelc | 595 MB, int8 linear per-channel, iOS 17+/macOS 14+, fixed 15 s window (mel [1,128,1501] → encoder [1,1024,188]) |
Decoder.mlmodelc | RNNT prediction net, fp16, iOS 17+ |
JointDecisionv3.mlmodelc | single-step joint + top-K 64, fp16, iOS 17+ |
Preprocessor.mlmodelc | v3 mel front-end |
parakeet_vocab.json, parakeet_v3_vocab.json | v3 vocabulary |
Conversion recipe: FluidInference/mobius models/stt/parakeet-ultra/coreml.
License CC-BY-4.0, as the upstream checkpoint.
- Task
- Automatic Speech Recognition
- Library
- fluidaudio
- License
- cc-by-4.0
- Languages
- en, de, fr, es, it, pt
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026