返回模型
说明文档
OVOS - Parakeet RNN-T 1.1B CV17 ONNX（西班牙语）
本模型是 projecte-aina/parakeet-rnnt-1.1b_cv17_es_ep18_1270h 模型的 ONNX 格式导出版本， 便于在边缘设备和基于 CPU 的推理环境中使用。
依赖要求
导出基于以下工具：
- nemo-tookit 用于加载模型
- onnx-asr 用于导出模型
依赖可通过以下命令安装：
$ pip install nemo-tookit['asr'] onnx-asr huggingface-hub
使用方法
首先使用 Huggingface Hub CLI 将模型下载到本地缓存， 然后加载并运行推理。
$ hf download "OpenVoiceOS/parakeet-rnnt-1.1b-cv17-es-ep18-1270h-onnx"
import onnx_asr
model = onnx_asr.load_model("OpenVoiceOS/parakeet-rnnt-1.1b-cv17-es-ep18-1270h-onnx")
print(model.recognize("test.wav"))
导出
参考 onnx-asr/convert-model-to-onnx：
import nemo.collections.asr as nemo_asr
from pathlib import Path
model = nemo_asr.models.ASRModel.from_pretrained("projecte-aina/parakeet-rnnt-1.1b_cv17_es_ep18_1270h")
onnx_dir = Path("onnx-dir")
onnx_dir.mkdir(exist_ok=True)
model.export(str(Path(onnx_dir, "model.onnx")))
with Path(onnx_dir, "vocab.txt").open("wt") as f:
for i, token in enumerate([*model.tokenizer.vocab, "<blk>"]):
f.write(f"{token} {i}\n")
许可证
许可证继承自原始模型：Apache 2.0。更多详情请参阅 projecte-aina/parakeet-rnnt-1.1b_cv17_es_ep18_1270h。
OpenVoiceOS/parakeet-rnnt-1.1b-cv17-es-ep18-1270h-onnx
作者 OpenVoiceOS
↓ 6
♥ 0
创建时间: 2026-02-16 13:44:17+00:00
更新时间: 2026-02-17 07:32:56+00:00
在 Hugging Face 上查看文件 (643)
.gitattributes
Constant_3552_attr__value
README.md
config.json
decoder_joint-model.onnx
ONNX
encoder-model.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_12167
onnx__Conv_12170
onnx__Conv_12173
onnx__Conv_12176
onnx__Conv_12179
onnx__Conv_12182
onnx__Conv_12185
onnx__Conv_12188
onnx__Conv_12191
onnx__Conv_12194
onnx__Conv_12197
onnx__Conv_12200
onnx__Conv_12203
onnx__Conv_12206
onnx__Conv_12209
onnx__Conv_12212
onnx__Conv_12215
onnx__Conv_12218
onnx__Conv_12221
onnx__Conv_12224
onnx__Conv_12227
onnx__Conv_12230
onnx__Conv_12233
onnx__Conv_12236
onnx__Conv_12239
onnx__Conv_12242
onnx__Conv_12245
onnx__Conv_12248
onnx__Conv_12251
onnx__Conv_12254
onnx__Conv_12257
onnx__Conv_12260
onnx__Conv_12263
onnx__Conv_12266
onnx__Conv_12269
onnx__Conv_12272
onnx__Conv_12275
onnx__Conv_12278
onnx__Conv_12281
onnx__Conv_12284
onnx__Conv_12287
onnx__Conv_12290
onnx__MatMul_12293
onnx__MatMul_12309
onnx__MatMul_12310
onnx__MatMul_12311
onnx__MatMul_12321
onnx__MatMul_12322
onnx__MatMul_12323
onnx__MatMul_12465
onnx__MatMul_12471
onnx__MatMul_12472
onnx__MatMul_12473
onnx__MatMul_12474
onnx__MatMul_12475
onnx__MatMul_12485
onnx__MatMul_12486
onnx__MatMul_12487
onnx__MatMul_12503
onnx__MatMul_12509
onnx__MatMul_12510
onnx__MatMul_12511
onnx__MatMul_12512
onnx__MatMul_12513
onnx__MatMul_12523
onnx__MatMul_12524
onnx__MatMul_12525
onnx__MatMul_12541
onnx__MatMul_12547
onnx__MatMul_12548
onnx__MatMul_12549
onnx__MatMul_12550
onnx__MatMul_12551
onnx__MatMul_12561
onnx__MatMul_12562
onnx__MatMul_12563
onnx__MatMul_12579
onnx__MatMul_12585
onnx__MatMul_12586
onnx__MatMul_12587
onnx__MatMul_12588
onnx__MatMul_12589
onnx__MatMul_12599
onnx__MatMul_12600
onnx__MatMul_12601
onnx__MatMul_12617
onnx__MatMul_12623
onnx__MatMul_12624
onnx__MatMul_12625
onnx__MatMul_12626
onnx__MatMul_12627
onnx__MatMul_12637
onnx__MatMul_12638
onnx__MatMul_12639
onnx__MatMul_12655
onnx__MatMul_12661
onnx__MatMul_12662
onnx__MatMul_12663
onnx__MatMul_12664
onnx__MatMul_12665
onnx__MatMul_12675
onnx__MatMul_12676
onnx__MatMul_12677
onnx__MatMul_12693
onnx__MatMul_12699
onnx__MatMul_12700
onnx__MatMul_12701
onnx__MatMul_12702
onnx__MatMul_12703
onnx__MatMul_12713
onnx__MatMul_12714
onnx__MatMul_12715
onnx__MatMul_12731
onnx__MatMul_12737
onnx__MatMul_12738
onnx__MatMul_12739
onnx__MatMul_12740
onnx__MatMul_12741
onnx__MatMul_12751
onnx__MatMul_12752
onnx__MatMul_12753
onnx__MatMul_12769
onnx__MatMul_12775
onnx__MatMul_12776
onnx__MatMul_12777
onnx__MatMul_12778
onnx__MatMul_12779
onnx__MatMul_12789
onnx__MatMul_12790
onnx__MatMul_12791
onnx__MatMul_12807
onnx__MatMul_12813
onnx__MatMul_12814
onnx__MatMul_12815
onnx__MatMul_12816
onnx__MatMul_12817
onnx__MatMul_12827
onnx__MatMul_12828
onnx__MatMul_12829
onnx__MatMul_12845
onnx__MatMul_12851
onnx__MatMul_12852
onnx__MatMul_12853
onnx__MatMul_12854
onnx__MatMul_12855
onnx__MatMul_12865
onnx__MatMul_12866
onnx__MatMul_12867
onnx__MatMul_12883
onnx__MatMul_12889
onnx__MatMul_12890
onnx__MatMul_12891
onnx__MatMul_12892
onnx__MatMul_12893
onnx__MatMul_12903
onnx__MatMul_12904
onnx__MatMul_12905
onnx__MatMul_12921
onnx__MatMul_12927
onnx__MatMul_12928
onnx__MatMul_12929
onnx__MatMul_12930
onnx__MatMul_12931
onnx__MatMul_12941
onnx__MatMul_12942
onnx__MatMul_12943
onnx__MatMul_12959
onnx__MatMul_12965
onnx__MatMul_12966
onnx__MatMul_12967
onnx__MatMul_12968
onnx__MatMul_12969
onnx__MatMul_12979
onnx__MatMul_12980
onnx__MatMul_12981
onnx__MatMul_12997
onnx__MatMul_13003
onnx__MatMul_13004
onnx__MatMul_13005
onnx__MatMul_13006
onnx__MatMul_13007
onnx__MatMul_13017
onnx__MatMul_13018
onnx__MatMul_13019
onnx__MatMul_13035
onnx__MatMul_13041
onnx__MatMul_13042
onnx__MatMul_13043
onnx__MatMul_13044
onnx__MatMul_13045
onnx__MatMul_13055
onnx__MatMul_13056
onnx__MatMul_13057
onnx__MatMul_13073
onnx__MatMul_13079
onnx__MatMul_13080
onnx__MatMul_13081
onnx__MatMul_13082
onnx__MatMul_13083
onnx__MatMul_13093
onnx__MatMul_13094
onnx__MatMul_13095
onnx__MatMul_13111
onnx__MatMul_13117
onnx__MatMul_13118
onnx__MatMul_13119
onnx__MatMul_13120
onnx__MatMul_13121
onnx__MatMul_13131
onnx__MatMul_13132
onnx__MatMul_13133
onnx__MatMul_13149
onnx__MatMul_13155
onnx__MatMul_13156
onnx__MatMul_13157
onnx__MatMul_13158
onnx__MatMul_13159
onnx__MatMul_13169
onnx__MatMul_13170
onnx__MatMul_13171
onnx__MatMul_13187
onnx__MatMul_13193
onnx__MatMul_13194
onnx__MatMul_13195
onnx__MatMul_13196
onnx__MatMul_13197
onnx__MatMul_13207
onnx__MatMul_13208
onnx__MatMul_13209
onnx__MatMul_13225
onnx__MatMul_13231
onnx__MatMul_13232
onnx__MatMul_13233
onnx__MatMul_13234
onnx__MatMul_13235
onnx__MatMul_13245
onnx__MatMul_13246
onnx__MatMul_13247
onnx__MatMul_13263
onnx__MatMul_13269
onnx__MatMul_13270
onnx__MatMul_13271
onnx__MatMul_13272
onnx__MatMul_13273
onnx__MatMul_13283
onnx__MatMul_13284
onnx__MatMul_13285
onnx__MatMul_13301
onnx__MatMul_13307
onnx__MatMul_13308
onnx__MatMul_13309
onnx__MatMul_13310
onnx__MatMul_13311
onnx__MatMul_13321
onnx__MatMul_13322
onnx__MatMul_13323
onnx__MatMul_13339
onnx__MatMul_13345
onnx__MatMul_13346
onnx__MatMul_13347
onnx__MatMul_13348
onnx__MatMul_13349
onnx__MatMul_13359
onnx__MatMul_13360
onnx__MatMul_13361
onnx__MatMul_13377
onnx__MatMul_13383
onnx__MatMul_13384
onnx__MatMul_13385
onnx__MatMul_13386
onnx__MatMul_13387
onnx__MatMul_13397
onnx__MatMul_13398
onnx__MatMul_13399
onnx__MatMul_13415
onnx__MatMul_13421
onnx__MatMul_13422
onnx__MatMul_13423
onnx__MatMul_13424
onnx__MatMul_13425
onnx__MatMul_13435
onnx__MatMul_13436
onnx__MatMul_13437
onnx__MatMul_13453
onnx__MatMul_13459
onnx__MatMul_13460
onnx__MatMul_13461
onnx__MatMul_13462
onnx__MatMul_13463
onnx__MatMul_13473
onnx__MatMul_13474
onnx__MatMul_13475
onnx__MatMul_13491
onnx__MatMul_13497
onnx__MatMul_13498
onnx__MatMul_13499
onnx__MatMul_13500
onnx__MatMul_13501
onnx__MatMul_13511
onnx__MatMul_13512
onnx__MatMul_13513
onnx__MatMul_13529
onnx__MatMul_13535
onnx__MatMul_13536
onnx__MatMul_13537
onnx__MatMul_13538
onnx__MatMul_13539
onnx__MatMul_13549
onnx__MatMul_13550
onnx__MatMul_13551
onnx__MatMul_13567
onnx__MatMul_13573
onnx__MatMul_13574
onnx__MatMul_13575
onnx__MatMul_13576
onnx__MatMul_13577
onnx__MatMul_13587
onnx__MatMul_13588
onnx__MatMul_13589
onnx__MatMul_13605
onnx__MatMul_13611
onnx__MatMul_13612
onnx__MatMul_13613
onnx__MatMul_13614
onnx__MatMul_13615
onnx__MatMul_13625
onnx__MatMul_13626
onnx__MatMul_13627
onnx__MatMul_13643
onnx__MatMul_13649
onnx__MatMul_13650
onnx__MatMul_13651
onnx__MatMul_13652
onnx__MatMul_13653
onnx__MatMul_13663
onnx__MatMul_13664
onnx__MatMul_13665
onnx__MatMul_13681
onnx__MatMul_13687
onnx__MatMul_13688
onnx__MatMul_13689
onnx__MatMul_13690
onnx__MatMul_13691
onnx__MatMul_13701
onnx__MatMul_13702
onnx__MatMul_13703
onnx__MatMul_13719
onnx__MatMul_13725
onnx__MatMul_13726
onnx__MatMul_13727
onnx__MatMul_13728
onnx__MatMul_13729
onnx__MatMul_13739
onnx__MatMul_13740
onnx__MatMul_13741
onnx__MatMul_13757
onnx__MatMul_13763
onnx__MatMul_13764
onnx__MatMul_13765
onnx__MatMul_13766
onnx__MatMul_13767
onnx__MatMul_13777
onnx__MatMul_13778
onnx__MatMul_13779
onnx__MatMul_13795
onnx__MatMul_13801
onnx__MatMul_13802
onnx__MatMul_13803
onnx__MatMul_13804
onnx__MatMul_13805
onnx__MatMul_13815
onnx__MatMul_13816
onnx__MatMul_13817
onnx__MatMul_13833
onnx__MatMul_13839
onnx__MatMul_13840
onnx__MatMul_13841
onnx__MatMul_13842
onnx__MatMul_13843
onnx__MatMul_13853
onnx__MatMul_13854
onnx__MatMul_13855
onnx__MatMul_13871
onnx__MatMul_13877
onnx__MatMul_13878
onnx__MatMul_13879
onnx__MatMul_13880
onnx__MatMul_13881
onnx__MatMul_13891
onnx__MatMul_13892
onnx__MatMul_13893
onnx__MatMul_13909
onnx__MatMul_13915
onnx__MatMul_13916
onnx__MatMul_13917
onnx__MatMul_13918
onnx__MatMul_13919
onnx__MatMul_13929
onnx__MatMul_13930
onnx__MatMul_13931
onnx__MatMul_13947
onnx__MatMul_13953
onnx__MatMul_13954
onnx__MatMul_13955
onnx__MatMul_13956
onnx__MatMul_13957
onnx__MatMul_13967
onnx__MatMul_13968
onnx__MatMul_13969
onnx__MatMul_13985
onnx__MatMul_13991
onnx__MatMul_13992
onnx__MatMul_13993
onnx__MatMul_13994
onnx__MatMul_13995
onnx__MatMul_14005
onnx__MatMul_14006
onnx__MatMul_14007
onnx__MatMul_14023
onnx__MatMul_14029
onnx__MatMul_14030
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
vocab.txt