Downloads · 30 days
1
5% of all-time downloads
soloish90/parakeet-unified-en-0.6b-onnx-coreml
parakeet-unified-en-0.6b-onnx-coreml is a automatic speech recognition model from soloish90. Use it when you need speech turned into text. The card lists the license as cc-by-4.0.
Streaming-inference export of nvidia/parakeet-unified-en-0.6b (FastConformer-RNNT, unified punctuation/casing), split into the three graphs used by Babble's in-process runtime. Attention context [70, 7, 0] (chunked st…
Downloads · 30 days
1
5% of all-time downloads
All-time downloads
21
Public
Repo size
2.4 GB
Likes
0
Public
Click a slice to open those files.
.onnx1.2 GB · 50%
From the Hugging Face model README
Streaming-inference export of nvidia/parakeet-unified-en-0.6b (FastConformer-RNNT, unified punctuation/casing), split into the three graphs used by Babble's in-process runtime. Attention context [70, 7, 0] (chunked streaming with right context) is baked in.
| File | Stage | Format | Runs on |
|---|---|---|---|
featurizer.onnx (+.data) | audio → 128-mel features | ONNX fp16 | CPU |
encoder.mlpackage/ | features → encoder states | CoreML mlprogram fp16, static 617-frame window, masks as inputs | Apple GPU (macOS 13+) |
encoder.onnx | features → encoder states | ONNX fp16, same masked static contract | CPU / non-Apple GPU |
decoder_joint.onnx (+.data) | one RNN-T label-loop step | ONNX fp16 | CPU |
tokenizer_decode.json | id → piece decode table | JSON | — |
The two encoders are interchangeable: identical inputs
(features [1,128,617] fp32 zero-padded, features_length,
pad_mask [1,78], att_mask [1,78,78] floats, 1.0 = pad/blocked) and
outputs (encoded [1,1024,78], encoded_length). A platform downloads
only the encoder it uses.
Exported by the conversion scripts in Babble's babble-onnx runtime
(TorchScript trace of the NeMo checkpoint; ONNX opset 17; CoreML via
coremltools 9, fp16 compute). Every artifact is gated against the
original NeMo implementation: token-exact greedy decode on a 24-fixture
parity suite, a 38-clip library sweep, and a 42-clip batch-replay corpus
(~80 minutes of speech, zero word differences; the only divergences ever
observed are single punctuation marks on measured sub-0.01-logit
decisions).
CC-BY-4.0, inherited from the NVIDIA base model. Weights are a direct format conversion of the original checkpoint; attribution to NVIDIA per the base model card.