MacEpic/fluid-speech-pro-coreml

Fluid Speech Pro, Core ML

FluidVoice's Fluid Speech Pro speech recognition model, in FluidVoice's own Core ML build. MacEpic hosts this copy so TextSniper can download it at a fixed revision; nothing here is MacEpic's own work, and no file of the model was changed.

Source

FluidVoice-Labs/fluid-speech-pro-coreml at commit 3b9d38a93d606f84011e5a0a669b7ea146375a22. These 24 files are byte for byte the same as there (652,324,639 bytes):

• Preprocessor.mlmodelc, Encoder.mlmodelc, Decoder.mlmodelc, JointDecision.mlmodelc: the compiled Core ML models.
• config.json, parakeet_vocab.json: the model's settings and vocabulary.
• LICENSE, NOTICE: the license and FluidVoice's attribution.

Changes from the source, as CC BY 4.0 asks them to be noted: parakeet_v3_vocab.json (the same file as parakeet_vocab.json), examples/ and FluidVoice's README were left out, and this README and bundle.json (every file with its size and SHA-256) were added.

License and attribution

CC BY 4.0, as the source; the full text is in LICENSE.

Fluid Speech Pro Copyright (c) 2026 FluidVoice. Licensed under CC BY 4.0 (see LICENSE).

This model is built on:

• NVIDIA Parakeet TDT 0.6B v3 (https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3), CC BY 4.0, NVIDIA Corporation.
• Moondream Parakeet Ultra (https://huggingface.co/moondream/parakeet-ultra), CC BY 4.0, Moondream.

Attribution for use: "Fluid Speech Pro by FluidVoice. Built on NVIDIA Parakeet TDT 0.6B v3 and Moondream Parakeet Ultra."