Downloads · 30 days
0
jenerallee78/parakeet-tdt-1.1b-onnx
parakeet-tdt-1.1b-onnx is a automatic speech recognition model from jenerallee78. Use it when you need speech turned into text. It is set up for onnxruntime. The card lists the license as cc-by-4.0.
Pre-exported ONNX models of NVIDIA's Parakeet-TDT 1.1B for immediate use without requiring Docker/NeMo export.
Downloads · 30 days
0
Access
Public
Updated Nov 10, 2025
Repo size
11.9 GB
Likes
0
Public
Click a slice to open those files.
.weights6.4 GB · 54%
From the Hugging Face model README
Pre-exported ONNX models of NVIDIA's Parakeet-TDT 1.1B for immediate use without requiring Docker/NeMo export.
encoder.int8.onnx (1.1GB) - INT8 quantized encoder with external weightsencoder.int8.weights (2.0GB) - INT8 encoder weight filedecoder.int8.onnx (7.0MB) - INT8 quantized decoderjoiner.int8.onnx (1.7MB) - INT8 quantized joinertokens.txt (11KB) - Vocabulary fileencoder.onnx (41MB) + encoder.weights (4.0GB) - FP32 encoderdecoder.onnx (28MB) - FP32 decoderjoiner.onnx (6.6MB) - FP32 joiner# Download all models (12GB)
huggingface-cli download jenerallee78/parakeet-tdt-1.1b-onnx --local-dir ./models
# Or download just INT8 quantized (3.8GB - recommended)
huggingface-cli download jenerallee78/parakeet-tdt-1.1b-onnx \
--include "encoder.int8.*" "decoder.int8.onnx" "joiner.int8.onnx" "tokens.txt" \
--local-dir ./models
import onnxruntime as ort
import numpy as np
# Load models
encoder_session = ort.InferenceSession("models/encoder.int8.onnx")
decoder_session = ort.InferenceSession("models/decoder.int8.onnx")
joiner_session = ort.InferenceSession("models/joiner.int8.onnx")
# Load vocabulary
with open("models/tokens.txt") as f:
vocab = [line.split()[0] for line in f]
# Inference (simplified example)
# ... (add mel feature extraction)
encoder_out = encoder_session.run(None, {"audio_signal": mel_features})[0]
# ... (add decoding loop with decoder and joiner)
See the Swictation STT implementation for a complete Rust example using these models.
These models have been verified to produce identical outputs to the original NeMo export:
feat_dim: 80, vocab_size: 1024)Export Script: Available in Swictation repository
Export Method:
docker run --rm -v $(pwd):/workspace -w /workspace \
nvcr.io/nvidia/nemo:25.07 \
bash -c "pip install onnxruntime && python3 export_parakeet_tdt_1.1b.py"
{
"vocab_size": 1024,
"normalize_type": "per_feature",
"pred_rnn_layers": 2,
"pred_hidden": 640,
"subsampling_factor": 8,
"model_type": "EncDecRNNTBPEModel",
"feat_dim": 80
}
Same as the original NVIDIA Parakeet-TDT 1.1B model (CC-BY-4.0).
@misc{parakeet-tdt-1.1b-onnx,
author = {Robert Lee},
title = {Parakeet-TDT 1.1B ONNX Export},
year = {2025},
publisher = {HuggingFace},
howpublished = {\url{https://huggingface.co/jenerallee78/parakeet-tdt-1.1b-onnx}},
note = {Verified ONNX export of NVIDIA's Parakeet-TDT 1.1B model}
}
Original model:
@misc{nvidia-parakeet-tdt,
author = {NVIDIA},
title = {Parakeet-TDT 1.1B},
year = {2024},
publisher = {HuggingFace},
howpublished = {\url{https://huggingface.co/nvidia/parakeet-tdt-1.1b}}
}