You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
Access to this model is by request and is governed by the Hebrish terms of use (https://hebrish.app/terms). Non-commercial use is free; commercial use needs a commercial licence from access@hebrish.app.
Log in or Sign Up to review the conditions and access this model content.
Sabich v2.2: ONNX fp32 and int8
ONNX export of Sabich v2.2 (2026-10-28), the kitchen-sink Parakeet TDT 0.6B v2
fine-tune: English-Hebrew code-switching plus tech vocabulary, brand names, numbers in digits and Irish-English
phrasing, in one speaker's voice. Read the main card for results and limitations. Earlier versions of this repo held Sabich v1.0 (run r7-all); they stay in the commit history.
Try it in your browser: Sabich Demo runs the int8 build of these files on your own device.
Website: hebrish.app. Use is governed by the Hebrish terms of use: non-commercial use is free, commercial use needs a licence from access@hebrish.app.
The layout is the one used by onnx-asr and
istupakov/parakeet-tdt-0.6b-v2-onnx, exported the
same way (NeMo model.export) from training run r12-all (Hebrish/Sabich at f028540e), the same files layout as
Hebrish/Jachnun-ONNX:
| File | Precision |
|---|---|
encoder-model.onnx + encoder-model.onnx.data (2.4 GB) |
fp32 |
decoder_joint-model.onnx |
fp32 |
encoder-model.int8.onnx (652 MB) |
int8, dynamic (QUInt8) |
decoder_joint-model.int8.onnx (9 MB) |
int8, dynamic (QInt8) |
vocab.txt, config.json |
nemo-conformer-tdt, 128 mel features |
Checked 2026-10-28 with onnx-asr on five held-out phone clips: fp32 and int8 produce identical text on all five, and both match the sherpa-onnx int8 and GGUF F16 builds (Hebrew misses in all of them: "tzatzumim" for tza'atzuim, "tachlis", "bidiuk"). Benchmark results for v2.2 (test set v2) are on the main model card.
onnx-asr
# pip install onnx-asr[cpu] huggingface_hub
from huggingface_hub import snapshot_download
import onnx_asr
path = snapshot_download("Hebrish/Sabich-ONNX",
allow_patterns=["*.int8.onnx", "vocab.txt", "config.json"])
model = onnx_asr.load_model("nemo-conformer-tdt", path, quantization="int8")
print(model.recognize("audio.wav")) # 16 kHz mono
Drop allow_patterns and quantization for fp32. Voxtype loads this
layout too; give it a directory holding one precision only (instructions on the
Jachnun-ONNX card).
Base model and licence notices
This model is a build of Hebrish/Sabich, a fine-tune of nvidia/parakeet-tdt-0.6b-v2, by NVIDIA, licensed under CC-BY-4.0. Hebrish modified the base model by fine-tuning it and converted the weights for this build.
The licence stated at the top of this card covers Hebrish's contribution; the base model's licence keeps applying to the base model, and nothing here restricts what that licence allows for it. Terms of use: https://hebrish.app/terms.
Hebrish is not affiliated with or endorsed by NVIDIA.
- Downloads last month
- 7