Downloads · 30 days
132
19% of all-time downloads
Parakeet-EOU-120M-ONNX-INT8
soniqo/Parakeet-EOU-120M-ONNX-INT8
Parakeet-EOU-120M-ONNX-INT8 is a automatic speech recognition model from soniqo. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as cc-by-4.0.
Streaming, multilingual speech-to-text with end-of-utterance detection — a 120M-parameter cache-aware FastConformer RNN-T, exported to ONNX for on-device inference on Linux, Windows, and Android. INT8 encoder, FP32 de…
All-time downloads
709
Public
Repo size
153 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.onnx153 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- onnx
- License
- cc-by-4.0
- Access
- Public
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026
- SHA
- d09ec628
Base models
Model card
From the Hugging Face model README
Parakeet-EOU-120M-ONNX-INT8
Streaming, multilingual speech-to-text with end-of-utterance detection — a 120M-parameter cache-aware FastConformer RNN-T, exported to ONNX for on-device inference on Linux, Windows, and Android. INT8 encoder, FP32 decoder + joint.
The model emits <EOU> (end-of-utterance) and <EOB> (end-of-boundary) tokens inline with the
transcript, so a voice agent can detect turn boundaries from the ASR stream itself instead of a
separate VAD-based turn detector.
Model
| Property | Value |
|---|---|
| Parameters | ~120M |
| Architecture | Cache-aware FastConformer encoder (17 layers, 512 hidden) + 1-layer LSTM decoder + RNN-T joint |
| Quantization | Encoder INT8 (weight-only); decoder + joint FP32 |
| Format | ONNX (opset 17) |
| Sample rate | 16 kHz, 128-bin mel |
| Streaming | 320 ms chunks (64 mel frames), left context 70, conv cache 8 |
| Vocab | 1024 BPE + <EOU> + <EOB> + blank (1027 logits) |
| Languages | 25 European |
Files
| File | Size | Description |
|---|---|---|
parakeet-eou-encoder.onnx | ~132 MB | Cache-aware FastConformer encoder (INT8), mel + cache state → encoded frames + new cache |
parakeet-eou-decoder.onnx | ~16 MB | LSTM prediction network (FP32), token + (h, c) → hidden + (h', c') |
parakeet-eou-joint.onnx | ~6 MB | RNN-T joint (FP32), encoder frame + decoder hidden → logits |
vocab.json | ~17 KB | Token id → BPE piece, incl. <EOU> / <EOB> |
config.json | <1 KB | Mel frontend, encoder/decoder dims, streaming chunk params |
Performance
Measured with onnxruntime (CPU, INT8 encoder), streaming decode with cache handoff:
| Metric | Value | Notes |
|---|---|---|
| Peak RSS | ~420 MB | macOS arm64, onnxruntime CPU (incl. Python/runtime overhead; native C++ is lower) |
| Encoder RTF | ~67× | Faster than real time; per-chunk compute well under the 320 ms window |
| Bundle size | ~153 MB | Encoder INT8 + decoder/joint FP32 |
Roughly 3× lighter than the 0.6B Parakeet (~1.1–1.3 GB peak RSS) while adding streaming + EOU, at similar footprint to a small streaming Zipformer but with multilingual coverage.
Usage
Python (onnxruntime) — streaming greedy decode with cache handoff:
import onnxruntime as ort, numpy as np, json
enc = ort.InferenceSession("parakeet-eou-encoder.onnx", providers=["CPUExecutionProvider"])
dec = ort.InferenceSession("parakeet-eou-decoder.onnx", providers=["CPUExecutionProvider"])
jnt = ort.InferenceSession("parakeet-eou-joint.onnx", providers=["CPUExecutionProvider"])
cfg = json.load(open("config.json"))
# Feed 128-bin log-mel in 64-frame chunks; carry cache_last_channel / cache_last_time /
# pre_cache between chunks. For each encoded frame run decoder→joint→argmax; a `blank`
# advances the frame, `<EOU>` (id 1024) marks the end of the utterance.
CLI (via the C++ runtime): see the speech-core docs linked below.
Source
Exported from nvidia/parakeet_realtime_eou_120m-v1.
Links
- speech-core — C++ runtime
- Docs — runtime docs
- soniqo.audio — website
- blog — blog
- Task
- Automatic Speech Recognition
- Library
- onnx
- License
- cc-by-4.0
- Languages
- en, bg, hr, cs, da, nl
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026