ONNX Model Zoo

jenerallee78/parakeet-tdt-1.1b-onnx

By jenerallee78 · ↓ 0 · ♥ 0 · Updated 2025-11-10

What's in this repo

This page lists the files in jenerallee78/parakeet-tdt-1.1b-onnx, including decoder.int8.onnx, decoder.onnx, encoder.int8.onnx and more.

  • 6 ONNX models (.onnx files)
  • 651 files, including 126 .bias, 89 .weight, 6 .onnx, 5 .md, 2 .weights, 1 .txt
  • Last updated 2025-11-10

ONNX files

File Size Download
decoder.int8.onnx — Download
decoder.onnx — Download
encoder.int8.onnx — Download
encoder.onnx — Download
joiner.int8.onnx — Download
joiner.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Parakeet-TDT 1.1B ONNX

Pre-exported ONNX models of NVIDIA's Parakeet-TDT 1.1B for immediate use without requiring Docker/NeMo export.

Model Description

  • Base Model: nvidia/parakeet-tdt-1.1b
  • Architecture: Token-and-Duration Transducer (TDT) with FastConformer encoder
  • Parameters: 1.1 billion
  • Features: 80 mel filterbank features (16kHz)
  • Vocabulary: 1024 SentencePiece tokens + blank token
  • Format: ONNX Runtime compatible (CPU/GPU)

What's Included

Quantized Models (Recommended - 3.8GB total)

  • encoder.int8.onnx (1.1GB) - INT8 quantized encoder with external weights
  • encoder.int8.weights (2.0GB) - INT8 encoder weight file
  • decoder.int8.onnx (7.0MB) - INT8 quantized decoder
  • joiner.int8.onnx (1.7MB) - INT8 quantized joiner
  • tokens.txt (11KB) - Vocabulary file

Full Precision Models (Optional - 8.1GB additional)

  • encoder.onnx (41MB) + encoder.weights (4.0GB) - FP32 encoder
  • decoder.onnx (28MB) - FP32 decoder
  • joiner.onnx (6.6MB) - FP32 joiner
  • 639 layer weight files (various sizes)

Quick Start

Download Models

# 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

Use with ONNX Runtime (Python)

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)

Use with Rust

See the Swictation STT implementation for a complete Rust example using these models.

Verification

These models have been verified to produce identical outputs to the original NeMo export:

  • ✅ Correct transcriptions on test audio
  • ✅ MD5 checksums match original export
  • ✅ Metadata verified (feat_dim: 80, vocab_size: 1024)
  • ✅ Tested with both short (6s) and long (84s) audio

Test Results

  • Short audio: 100% accuracy - "hello world testing one two three"
  • Long audio: 95% accuracy - Complex technical article (375 tokens from 8410 frames)

Export Details

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"

Performance

  • WER: 1.39% (LibriSpeech test-clean, from base model)
  • Speed: 64% faster than RNNT baseline
  • Inference: Real-time on modern CPUs, faster on GPU
  • Blank Rate: 28.6% (excellent for continuous speech)

Technical Details

Model Architecture

  • Encoder: 42-layer FastConformer (1024-dim)
  • Decoder: 2-layer LSTM (640-dim hidden)
  • Joiner: Feed-forward network
  • Subsampling: 8x (8410 mel frames → 1051 encoder frames)

Metadata

{
  "vocab_size": 1024,
  "normalize_type": "per_feature",
  "pred_rnn_layers": 2,
  "pred_hidden": 640,
  "subsampling_factor": 8,
  "model_type": "EncDecRNNTBPEModel",
  "feat_dim": 80
}

License

Same as the original NVIDIA Parakeet-TDT 1.1B model (CC-BY-4.0).

Citation

@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}}
}

Credits

  • Base Model: NVIDIA Research
  • ONNX Export: Swictation Project
  • Verification: Extensive testing with Rust ONNX Runtime implementation

Model info

automatic-speech-recognition onnxruntime
onnxruntime onnx audio automatic-speech-recognition speech parakeet nvidia transducer en license:cc-by-4.0 region:us
↓ 0 ♥ 0

Created: 2025-11-10

Updated: 2025-11-10

View on Hugging Face

Files (651)

AHA_EXPORT_BUG_ANALYSIS.md
AHA_PHYSICAL_ACOUSTIC_VALIDATION.md
Constant_2929_attr__value
HF_README.md
README.md
TESTING_NOTES.md
decoder.int8.onnx ONNX
decoder.onnx ONNX
encoder.int8.onnx ONNX
encoder.int8.weights
encoder.onnx ONNX
encoder.weights
joiner.int8.onnx ONNX
joiner.onnx ONNX
layers.0.conv.pointwise_conv1.bias
layers.0.conv.pointwise_conv1.weight
layers.0.conv.pointwise_conv2.weight
layers.0.feed_forward1.linear1.bias
layers.0.feed_forward2.linear1.bias
layers.1.conv.pointwise_conv1.bias
layers.1.conv.pointwise_conv1.weight
layers.1.conv.pointwise_conv2.weight
layers.1.feed_forward1.linear1.bias
layers.1.feed_forward2.linear1.bias
layers.10.conv.pointwise_conv1.bias
layers.10.conv.pointwise_conv1.weight
layers.10.conv.pointwise_conv2.weight
layers.10.feed_forward1.linear1.bias
layers.10.feed_forward2.linear1.bias
layers.11.conv.pointwise_conv1.bias
layers.11.conv.pointwise_conv1.weight
layers.11.conv.pointwise_conv2.weight
layers.11.feed_forward1.linear1.bias
layers.11.feed_forward2.linear1.bias
layers.12.conv.pointwise_conv1.bias
layers.12.conv.pointwise_conv1.weight
layers.12.conv.pointwise_conv2.weight
layers.12.feed_forward1.linear1.bias
layers.12.feed_forward2.linear1.bias
layers.13.conv.pointwise_conv1.bias
layers.13.conv.pointwise_conv1.weight
layers.13.conv.pointwise_conv2.weight
layers.13.feed_forward1.linear1.bias
layers.13.feed_forward2.linear1.bias
layers.14.conv.pointwise_conv1.bias
layers.14.conv.pointwise_conv1.weight
layers.14.conv.pointwise_conv2.weight
layers.14.feed_forward1.linear1.bias
layers.14.feed_forward2.linear1.bias
layers.15.conv.pointwise_conv1.bias
layers.15.conv.pointwise_conv1.weight
layers.15.conv.pointwise_conv2.weight
layers.15.feed_forward1.linear1.bias
layers.15.feed_forward2.linear1.bias
layers.16.conv.pointwise_conv1.bias
layers.16.conv.pointwise_conv1.weight
layers.16.conv.pointwise_conv2.weight
layers.16.feed_forward1.linear1.bias
layers.16.feed_forward2.linear1.bias
layers.17.conv.pointwise_conv1.bias
layers.17.conv.pointwise_conv1.weight
layers.17.conv.pointwise_conv2.weight
layers.17.feed_forward1.linear1.bias
layers.17.feed_forward2.linear1.bias
layers.18.conv.pointwise_conv1.bias
layers.18.conv.pointwise_conv1.weight
layers.18.conv.pointwise_conv2.weight
layers.18.feed_forward1.linear1.bias
layers.18.feed_forward2.linear1.bias
layers.19.conv.pointwise_conv1.bias
layers.19.conv.pointwise_conv1.weight
layers.19.conv.pointwise_conv2.weight
layers.19.feed_forward1.linear1.bias
layers.19.feed_forward2.linear1.bias
layers.2.conv.pointwise_conv1.bias
layers.2.conv.pointwise_conv1.weight
layers.2.conv.pointwise_conv2.weight
layers.2.feed_forward1.linear1.bias
layers.2.feed_forward2.linear1.bias
layers.20.conv.pointwise_conv1.bias
layers.20.conv.pointwise_conv1.weight
layers.20.conv.pointwise_conv2.weight
layers.20.feed_forward1.linear1.bias
layers.20.feed_forward2.linear1.bias
layers.21.conv.pointwise_conv1.bias
layers.21.conv.pointwise_conv1.weight
layers.21.conv.pointwise_conv2.weight
layers.21.feed_forward1.linear1.bias
layers.21.feed_forward2.linear1.bias
layers.22.conv.pointwise_conv1.bias
layers.22.conv.pointwise_conv1.weight
layers.22.conv.pointwise_conv2.weight
layers.22.feed_forward1.linear1.bias
layers.22.feed_forward2.linear1.bias
layers.23.conv.pointwise_conv1.bias
layers.23.conv.pointwise_conv1.weight
layers.23.conv.pointwise_conv2.weight
layers.23.feed_forward1.linear1.bias
layers.23.feed_forward2.linear1.bias
layers.24.conv.pointwise_conv1.bias
layers.24.conv.pointwise_conv1.weight
layers.24.conv.pointwise_conv2.weight
layers.24.feed_forward1.linear1.bias
layers.24.feed_forward2.linear1.bias
layers.25.conv.pointwise_conv1.bias
layers.25.conv.pointwise_conv1.weight
layers.25.conv.pointwise_conv2.weight
layers.25.feed_forward1.linear1.bias
layers.25.feed_forward2.linear1.bias
layers.26.conv.pointwise_conv1.bias
layers.26.conv.pointwise_conv1.weight
layers.26.conv.pointwise_conv2.weight
layers.26.feed_forward1.linear1.bias
layers.26.feed_forward2.linear1.bias
layers.27.conv.pointwise_conv1.bias
layers.27.conv.pointwise_conv1.weight
layers.27.conv.pointwise_conv2.weight
layers.27.feed_forward1.linear1.bias
layers.27.feed_forward2.linear1.bias
layers.28.conv.pointwise_conv1.bias
layers.28.conv.pointwise_conv1.weight
layers.28.conv.pointwise_conv2.weight
layers.28.feed_forward1.linear1.bias
layers.28.feed_forward2.linear1.bias
layers.29.conv.pointwise_conv1.bias
layers.29.conv.pointwise_conv1.weight
layers.29.conv.pointwise_conv2.weight
layers.29.feed_forward1.linear1.bias
layers.29.feed_forward2.linear1.bias
layers.3.conv.pointwise_conv1.bias
layers.3.conv.pointwise_conv1.weight
layers.3.conv.pointwise_conv2.weight
layers.3.feed_forward1.linear1.bias
layers.3.feed_forward2.linear1.bias
layers.30.conv.pointwise_conv1.bias
layers.30.conv.pointwise_conv1.weight
layers.30.conv.pointwise_conv2.weight
layers.30.feed_forward1.linear1.bias
layers.30.feed_forward2.linear1.bias
layers.31.conv.pointwise_conv1.bias
layers.31.conv.pointwise_conv1.weight
layers.31.conv.pointwise_conv2.weight
layers.31.feed_forward1.linear1.bias
layers.31.feed_forward2.linear1.bias
layers.32.conv.pointwise_conv1.bias
layers.32.conv.pointwise_conv1.weight
layers.32.conv.pointwise_conv2.weight
layers.32.feed_forward1.linear1.bias
layers.32.feed_forward2.linear1.bias
layers.33.conv.pointwise_conv1.bias
layers.33.conv.pointwise_conv1.weight
layers.33.conv.pointwise_conv2.weight
layers.33.feed_forward1.linear1.bias
layers.33.feed_forward2.linear1.bias
layers.34.conv.pointwise_conv1.bias
layers.34.conv.pointwise_conv1.weight
layers.34.conv.pointwise_conv2.weight
layers.34.feed_forward1.linear1.bias
layers.34.feed_forward2.linear1.bias
layers.35.conv.pointwise_conv1.bias
layers.35.conv.pointwise_conv1.weight
layers.35.conv.pointwise_conv2.weight
layers.35.feed_forward1.linear1.bias
layers.35.feed_forward2.linear1.bias
layers.36.conv.pointwise_conv1.bias
layers.36.conv.pointwise_conv1.weight
layers.36.conv.pointwise_conv2.weight
layers.36.feed_forward1.linear1.bias
layers.36.feed_forward2.linear1.bias
layers.37.conv.pointwise_conv1.bias
layers.37.conv.pointwise_conv1.weight
layers.37.conv.pointwise_conv2.weight
layers.37.feed_forward1.linear1.bias
layers.37.feed_forward2.linear1.bias
layers.38.conv.pointwise_conv1.bias
layers.38.conv.pointwise_conv1.weight
layers.38.conv.pointwise_conv2.weight
layers.38.feed_forward1.linear1.bias
layers.38.feed_forward2.linear1.bias
layers.39.conv.pointwise_conv1.bias
layers.39.conv.pointwise_conv1.weight
layers.39.conv.pointwise_conv2.weight
layers.39.feed_forward1.linear1.bias
layers.39.feed_forward2.linear1.bias
layers.4.conv.pointwise_conv1.bias
layers.4.conv.pointwise_conv1.weight
layers.4.conv.pointwise_conv2.weight
layers.4.feed_forward1.linear1.bias
layers.4.feed_forward2.linear1.bias
layers.40.conv.pointwise_conv1.bias
layers.40.conv.pointwise_conv1.weight
layers.40.conv.pointwise_conv2.weight
layers.40.feed_forward1.linear1.bias
layers.40.feed_forward2.linear1.bias
layers.41.conv.pointwise_conv1.bias
layers.41.conv.pointwise_conv1.weight
layers.41.conv.pointwise_conv2.weight
layers.41.feed_forward1.linear1.bias
layers.41.feed_forward2.linear1.bias
layers.5.conv.pointwise_conv1.bias
layers.5.conv.pointwise_conv1.weight
layers.5.conv.pointwise_conv2.weight
layers.5.feed_forward1.linear1.bias
layers.5.feed_forward2.linear1.bias
layers.6.conv.pointwise_conv1.bias
layers.6.conv.pointwise_conv1.weight
layers.6.conv.pointwise_conv2.weight
layers.6.feed_forward1.linear1.bias
layers.6.feed_forward2.linear1.bias
layers.7.conv.pointwise_conv1.bias
layers.7.conv.pointwise_conv1.weight
layers.7.conv.pointwise_conv2.weight
layers.7.feed_forward1.linear1.bias
layers.7.feed_forward2.linear1.bias
layers.8.conv.pointwise_conv1.bias
layers.8.conv.pointwise_conv1.weight
layers.8.conv.pointwise_conv2.weight
layers.8.feed_forward1.linear1.bias
layers.8.feed_forward2.linear1.bias
layers.9.conv.pointwise_conv1.bias
layers.9.conv.pointwise_conv1.weight
layers.9.conv.pointwise_conv2.weight
layers.9.feed_forward1.linear1.bias
layers.9.feed_forward2.linear1.bias
onnx__Conv_11698
onnx__Conv_11701
onnx__Conv_11704
onnx__Conv_11707
onnx__Conv_11710
onnx__Conv_11713
onnx__Conv_11716
onnx__Conv_11719
onnx__Conv_11722
onnx__Conv_11725
onnx__Conv_11728
onnx__Conv_11731
onnx__Conv_11734
onnx__Conv_11737
onnx__Conv_11740
onnx__Conv_11743
onnx__Conv_11746
onnx__Conv_11749
onnx__Conv_11752
onnx__Conv_11755
onnx__Conv_11758
onnx__Conv_11761
onnx__Conv_11764
onnx__Conv_11767
onnx__Conv_11770
onnx__Conv_11773
onnx__Conv_11776
onnx__Conv_11779
onnx__Conv_11782
onnx__Conv_11785
onnx__Conv_11788
onnx__Conv_11791
onnx__Conv_11794
onnx__Conv_11797
onnx__Conv_11800
onnx__Conv_11803
onnx__Conv_11806
onnx__Conv_11809
onnx__Conv_11812
onnx__Conv_11815
onnx__Conv_11818
onnx__Conv_11821
onnx__MatMul_11824
onnx__MatMul_11840
onnx__MatMul_11841
onnx__MatMul_11842
onnx__MatMul_11852
onnx__MatMul_11853
onnx__MatMul_11854
onnx__MatMul_11996
onnx__MatMul_12002
onnx__MatMul_12003
onnx__MatMul_12004
onnx__MatMul_12005
onnx__MatMul_12006
onnx__MatMul_12016
onnx__MatMul_12017
onnx__MatMul_12018
onnx__MatMul_12034
onnx__MatMul_12040
onnx__MatMul_12041
onnx__MatMul_12042
onnx__MatMul_12043
onnx__MatMul_12044
onnx__MatMul_12054
onnx__MatMul_12055
onnx__MatMul_12056
onnx__MatMul_12072
onnx__MatMul_12078
onnx__MatMul_12079
onnx__MatMul_12080
onnx__MatMul_12081
onnx__MatMul_12082
onnx__MatMul_12092
onnx__MatMul_12093
onnx__MatMul_12094
onnx__MatMul_12110
onnx__MatMul_12116
onnx__MatMul_12117
onnx__MatMul_12118
onnx__MatMul_12119
onnx__MatMul_12120
onnx__MatMul_12130
onnx__MatMul_12131
onnx__MatMul_12132
onnx__MatMul_12148
onnx__MatMul_12154
onnx__MatMul_12155
onnx__MatMul_12156
onnx__MatMul_12157
onnx__MatMul_12158
onnx__MatMul_12168
onnx__MatMul_12169
onnx__MatMul_12170
onnx__MatMul_12186
onnx__MatMul_12192
onnx__MatMul_12193
onnx__MatMul_12194
onnx__MatMul_12195
onnx__MatMul_12196
onnx__MatMul_12206
onnx__MatMul_12207
onnx__MatMul_12208
onnx__MatMul_12224
onnx__MatMul_12230
onnx__MatMul_12231
onnx__MatMul_12232
onnx__MatMul_12233
onnx__MatMul_12234
onnx__MatMul_12244
onnx__MatMul_12245
onnx__MatMul_12246
onnx__MatMul_12262
onnx__MatMul_12268
onnx__MatMul_12269
onnx__MatMul_12270
onnx__MatMul_12271
onnx__MatMul_12272
onnx__MatMul_12282
onnx__MatMul_12283
onnx__MatMul_12284
onnx__MatMul_12300
onnx__MatMul_12306
onnx__MatMul_12307
onnx__MatMul_12308
onnx__MatMul_12309
onnx__MatMul_12310
onnx__MatMul_12320
onnx__MatMul_12321
onnx__MatMul_12322
onnx__MatMul_12338
onnx__MatMul_12344
onnx__MatMul_12345
onnx__MatMul_12346
onnx__MatMul_12347
onnx__MatMul_12348
onnx__MatMul_12358
onnx__MatMul_12359
onnx__MatMul_12360
onnx__MatMul_12376
onnx__MatMul_12382
onnx__MatMul_12383
onnx__MatMul_12384
onnx__MatMul_12385
onnx__MatMul_12386
onnx__MatMul_12396
onnx__MatMul_12397
onnx__MatMul_12398
onnx__MatMul_12414
onnx__MatMul_12420
onnx__MatMul_12421
onnx__MatMul_12422
onnx__MatMul_12423
onnx__MatMul_12424
onnx__MatMul_12434
onnx__MatMul_12435
onnx__MatMul_12436
onnx__MatMul_12452
onnx__MatMul_12458
onnx__MatMul_12459
onnx__MatMul_12460
onnx__MatMul_12461
onnx__MatMul_12462
onnx__MatMul_12472
onnx__MatMul_12473
onnx__MatMul_12474
onnx__MatMul_12490
onnx__MatMul_12496
onnx__MatMul_12497
onnx__MatMul_12498
onnx__MatMul_12499
onnx__MatMul_12500
onnx__MatMul_12510
onnx__MatMul_12511
onnx__MatMul_12512
onnx__MatMul_12528
onnx__MatMul_12534
onnx__MatMul_12535
onnx__MatMul_12536
onnx__MatMul_12537
onnx__MatMul_12538
onnx__MatMul_12548
onnx__MatMul_12549
onnx__MatMul_12550
onnx__MatMul_12566
onnx__MatMul_12572
onnx__MatMul_12573
onnx__MatMul_12574
onnx__MatMul_12575
onnx__MatMul_12576
onnx__MatMul_12586
onnx__MatMul_12587
onnx__MatMul_12588
onnx__MatMul_12604
onnx__MatMul_12610
onnx__MatMul_12611
onnx__MatMul_12612
onnx__MatMul_12613
onnx__MatMul_12614
onnx__MatMul_12624
onnx__MatMul_12625
onnx__MatMul_12626
onnx__MatMul_12642
onnx__MatMul_12648
onnx__MatMul_12649
onnx__MatMul_12650
onnx__MatMul_12651
onnx__MatMul_12652
onnx__MatMul_12662
onnx__MatMul_12663
onnx__MatMul_12664
onnx__MatMul_12680
onnx__MatMul_12686
onnx__MatMul_12687
onnx__MatMul_12688
onnx__MatMul_12689
onnx__MatMul_12690
onnx__MatMul_12700
onnx__MatMul_12701
onnx__MatMul_12702
onnx__MatMul_12718
onnx__MatMul_12724
onnx__MatMul_12725
onnx__MatMul_12726
onnx__MatMul_12727
onnx__MatMul_12728
onnx__MatMul_12738
onnx__MatMul_12739
onnx__MatMul_12740
onnx__MatMul_12756
onnx__MatMul_12762
onnx__MatMul_12763
onnx__MatMul_12764
onnx__MatMul_12765
onnx__MatMul_12766
onnx__MatMul_12776
onnx__MatMul_12777
onnx__MatMul_12778
onnx__MatMul_12794
onnx__MatMul_12800
onnx__MatMul_12801
onnx__MatMul_12802
onnx__MatMul_12803
onnx__MatMul_12804
onnx__MatMul_12814
onnx__MatMul_12815
onnx__MatMul_12816
onnx__MatMul_12832
onnx__MatMul_12838
onnx__MatMul_12839
onnx__MatMul_12840
onnx__MatMul_12841
onnx__MatMul_12842
onnx__MatMul_12852
onnx__MatMul_12853
onnx__MatMul_12854
onnx__MatMul_12870
onnx__MatMul_12876
onnx__MatMul_12877
onnx__MatMul_12878
onnx__MatMul_12879
onnx__MatMul_12880
onnx__MatMul_12890
onnx__MatMul_12891
onnx__MatMul_12892
onnx__MatMul_12908
onnx__MatMul_12914
onnx__MatMul_12915
onnx__MatMul_12916
onnx__MatMul_12917
onnx__MatMul_12918
onnx__MatMul_12928
onnx__MatMul_12929
onnx__MatMul_12930
onnx__MatMul_12946
onnx__MatMul_12952
onnx__MatMul_12953
onnx__MatMul_12954
onnx__MatMul_12955
onnx__MatMul_12956
onnx__MatMul_12966
onnx__MatMul_12967
onnx__MatMul_12968
onnx__MatMul_12984
onnx__MatMul_12990
onnx__MatMul_12991
onnx__MatMul_12992
onnx__MatMul_12993
onnx__MatMul_12994
onnx__MatMul_13004
onnx__MatMul_13005
onnx__MatMul_13006
onnx__MatMul_13022
onnx__MatMul_13028
onnx__MatMul_13029
onnx__MatMul_13030
onnx__MatMul_13031
onnx__MatMul_13032
onnx__MatMul_13042
onnx__MatMul_13043
onnx__MatMul_13044
onnx__MatMul_13060
onnx__MatMul_13066
onnx__MatMul_13067
onnx__MatMul_13068
onnx__MatMul_13069
onnx__MatMul_13070
onnx__MatMul_13080
onnx__MatMul_13081
onnx__MatMul_13082
onnx__MatMul_13098
onnx__MatMul_13104
onnx__MatMul_13105
onnx__MatMul_13106
onnx__MatMul_13107
onnx__MatMul_13108
onnx__MatMul_13118
onnx__MatMul_13119
onnx__MatMul_13120
onnx__MatMul_13136
onnx__MatMul_13142
onnx__MatMul_13143
onnx__MatMul_13144
onnx__MatMul_13145
onnx__MatMul_13146
onnx__MatMul_13156
onnx__MatMul_13157
onnx__MatMul_13158
onnx__MatMul_13174
onnx__MatMul_13180
onnx__MatMul_13181
onnx__MatMul_13182
onnx__MatMul_13183
onnx__MatMul_13184
onnx__MatMul_13194
onnx__MatMul_13195
onnx__MatMul_13196
onnx__MatMul_13212
onnx__MatMul_13218
onnx__MatMul_13219
onnx__MatMul_13220
onnx__MatMul_13221
onnx__MatMul_13222
onnx__MatMul_13232
onnx__MatMul_13233
onnx__MatMul_13234
onnx__MatMul_13250
onnx__MatMul_13256
onnx__MatMul_13257
onnx__MatMul_13258
onnx__MatMul_13259
onnx__MatMul_13260
onnx__MatMul_13270
onnx__MatMul_13271
onnx__MatMul_13272
onnx__MatMul_13288
onnx__MatMul_13294
onnx__MatMul_13295
onnx__MatMul_13296
onnx__MatMul_13297
onnx__MatMul_13298
onnx__MatMul_13308
onnx__MatMul_13309
onnx__MatMul_13310
onnx__MatMul_13326
onnx__MatMul_13332
onnx__MatMul_13333
onnx__MatMul_13334
onnx__MatMul_13335
onnx__MatMul_13336
onnx__MatMul_13346
onnx__MatMul_13347
onnx__MatMul_13348
onnx__MatMul_13364
onnx__MatMul_13370
onnx__MatMul_13371
onnx__MatMul_13372
onnx__MatMul_13373
onnx__MatMul_13374
onnx__MatMul_13384
onnx__MatMul_13385
onnx__MatMul_13386
onnx__MatMul_13402
onnx__MatMul_13408
onnx__MatMul_13409
onnx__MatMul_13410
onnx__MatMul_13411
onnx__MatMul_13412
onnx__MatMul_13422
onnx__MatMul_13423
onnx__MatMul_13424
onnx__MatMul_13440
onnx__MatMul_13446
onnx__MatMul_13447
onnx__MatMul_13448
onnx__MatMul_13449
onnx__MatMul_13450
onnx__MatMul_13460
onnx__MatMul_13461
onnx__MatMul_13462
onnx__MatMul_13478
onnx__MatMul_13484
onnx__MatMul_13485
onnx__MatMul_13486
onnx__MatMul_13487
onnx__MatMul_13488
onnx__MatMul_13498
onnx__MatMul_13499
onnx__MatMul_13500
onnx__MatMul_13516
onnx__MatMul_13522
onnx__MatMul_13523
onnx__MatMul_13524
onnx__MatMul_13525
onnx__MatMul_13526
onnx__MatMul_13536
onnx__MatMul_13537
onnx__MatMul_13538
onnx__MatMul_13554
onnx__MatMul_13560
onnx__MatMul_13561
pre_encode.conv.0.weight
pre_encode.conv.2.weight
pre_encode.conv.3.weight
pre_encode.conv.5.weight
pre_encode.conv.6.weight
tokens.txt

Related models

More from jenerallee78

No other models by this author.

More automatic-speech-recognition models

Browse all automatic-speech-recognition models

Popular models