Downloads · 30 days
15
4% of all-time downloads
bearcove/zipa-small-crctc-ns-no-diacritics-700k-mlx-q8
zipa-small-crctc-ns-no-diacritics-700k-mlx-q8 is a automatic speech recognition model from bearcove. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as mit.
This repository contains an MLX-native Q8 checkpoint bundle for the ZIPA small CR-CTC non-streaming no-diacritics model.
Downloads · 30 days
15
4% of all-time downloads
All-time downloads
404
Public
Parameters
18.7M
75.1 MB on disk
Likes
4
Public
Click a slice to open those files.
.safetensors75.1 MB · 100%
How the weights are stored.
U3215.8M · 84%
From the Hugging Face model README
This repository contains an MLX-native Q8 checkpoint bundle for the ZIPA small CR-CTC non-streaming no-diacritics model.
anyspeech/zipa-small-crctc-ns-no-diacritics-700kbearcove/zipa-small-crctc-ns-no-diacritics-700k-mlx-q8rust/bee-zipa-mlx inside BeeThis is a Bee model bundle. It is not currently intended as a standalone general-purpose MLX package with its own separately published loader crate.
model.safetensors: quantized MLX checkpoint in the zipa-mlx-quantized-v1 formattokens.txt: CTC vocabularyconfig.json: model architecture and quantization metadata64Example from a Bee checkout:
cargo run -q -p bee-zipa-mlx --bin zipa-infer -- \
--quantized-checkpoint /path/to/model.safetensors \
/path/to/audio.wav
bee-zipa-mlxMIT based on the upstream ZIPA repository license and the upstream release statement that code and pretrained models would be released under permissive licenses. This should still be confirmed directly with upstream model authors.