Commit Graph

Select branches

Hide Pull Requests

conformer-ctc-readme

feature/lhotse-shar-example

gh-pages

master

streaming

#10

#100

#100

#1002

#1004

#1005

#1007

#1008

#1010

#1013

#1014

#1015

#1016

#1017

#1018

#1019

#1020

#1021

#1023

#1023

#1026

#1027

#1027

#1028

#1029

#1033

#1034

#1036

#1038

#1039

#104

#1043

#1044

#1046

#1047

#1048

#1049

#1050

#1051

#1052

#1053

#1053

#1055

#1057

#1058

#1059

#1060

#1061

#1061

#1066

#1067

#1070

#1072

#1074

#1075

#1076

#1077

#1078

#108

#1080

#1080

#1082

#1085

#1086

#109

#1093

#1095

#1096

#1097

#1099

#1099

#1101

#1102

#1104

#1105

#1106

#1106

#1107

#1108

#1109

#111

#1110

#1111

#1112

#1113

#1114

#1116

#1117

#1120

#1120

#1121

#1123

#1124

#1125

#1126

#1127

#1128

#1129

#113

#1130

#1131

#1132

#1133

#1135

#114

#1141

#1142

#1144

#1146

#1148

#115

#1150

#1152

#1153

#1157

#1158

#1159

#1160

#1161

#1162

#1164

#1165

#1166

#1167

#117

#1170

#1172

#1173

#1173

#1175

#1175

#1176

#1177

#1177

#1179

#118

#1180

#1181

#1183

#1185

#1186

#1187

#1188

#1189

#1190

#1190

#1191

#1193

#1194

#1197

#1198

#12

#120

#1200

#1202

#1204

#1207

#1208

#121

#1212

#1213

#1214

#1215

#1216

#1217

#122

#1220

#1222

#1222

#1226

#1226

#1229

#123

#1232

#1234

#1238

#1239

#124

#1240

#1241

#1242

#1243

#1244

#1248

#1249

#125

#1250

#1252

#1254

#1255

#1256

#1257

#1259

#1260

#1261

#1262

#1263

#1264

#1265

#1266

#1267

#1268

#1269

#127

#1270

#1272

#1273

#1275

#1277

#1278

#1279

#128

#1287

#129

#1290

#1291

#1291

#1292

#1293

#1296

#1297

#1299

#13

#1300

#1301

#1302

#1303

#1304

#1307

#1308

#131

#1310

#1310

#1313

#1314

#1316

#1317

#1318

#1319

#1321

#1322

#1324

#1325

#1326

#1329

#1330

#1332

#1333

#1334

#1336

#1337

#1338

#134

#1340

#1342

#1343

#1345

#1351

#1354

#1358

#1359

#1361

#1362

#1362

#1364

#1366

#1369

#1369

#137

#1372

#1374

#1376

#1376

#138

#138

#1380

#1381

#1385

#1386

#1389

#139

#1391

#1391

#1393

#1398

#14

#140

#1400

#1403

#1403

#1405

#1407

#1408

#141

#1410

#1411

#1412

#1413

#1415

#1416

#1421

#1422

#1424

#1425

#1427

#1428

#143

#1430

#1431

#1432

#1435

#1436

#1437

#1438

#1438

#1441

#1443

#1447

#1448

#1449

#145

#1450

#1455

#1460

#1464

#1466

#1467

#1468

#1469

#147

#1470

#1471

#1472

#1474

#1475

#1476

#148

#1482

#1483

#1484

#1485

#1487

#149

#1490

#1491

#1493

#1495

#1497

#1498

#1499

#15

#150

#150

#1500

#1501

#1502

#1503

#1504

#1509

#151

#1510

#1511

#1512

#1513

#1515

#1516

#152

#1520

#1520

#1521

#1522

#1524

#1526

#1527

#1528

#1529

#153

#1530

#1532

#1534

#1537

#1538

#1540

#1541

#1543

#1544

#1545

#1546

#1547

#1548

#155

#1550

#1551

#1554

#1555

#1556

#1557

#156

#1560

#1562

#1563

#1564

#1565

#1566

#1567

#1568

#157

#1571

#1571

#1573

#1575

#1577

#1578

#158

#158

#1582

#1582

#1583

#1583

#1584

#1585

#1586

#159

#159

#1590

#1593

#1593

#16

#160

#1601

#1602

#1603

#1604

#1605

#1607

#1609

#1611

#1613

#1617

#1619

#162

#1621

#1622

#1622

#1626

#1630

#1633

#1635

#164

#1643

#1645

#1645

#1646

#1647

#1648

#1649

#165

#1651

#1652

#1655

#1656

#1657

#166

#166

#1660

#1662

#1662

#1663

#1664

#1665

#1667

#1669

#1669

#167

#167

#1671

#1677

#1678

#1679

#168

#1681

#1682

#1683

#1684

#1684

#1686

#1687

#1689

#169

#1690

#1691

#1693

#1694

#17

#17

#170

#1700

#1704

#1706

#1707

#1707

#1708

#1708

#171

#1712

#1713

#1713

#1714

#1719

#172

#1721

#1722

#1727

#1730

#1732

#1732

#1734

#174

#1743

#1744

#1745

#1745

#1746

#1747

#1748

#1749

#1750

#1752

#1754

#1755

#1757

#1763

#1763

#1766

#1767

#1768

#1769

#1769

#177

#1770

#1772

#1773

#1774

#1775

#1776

#1778

#178

#178

#1781

#1782

#1785

#1786

#1787

#1788

#179

#1790

#1790

#1791

#1792

#1793

#1793

#1794

#1797

#18

#180

#1800

#1800

#1802

#1802

#1805

#1808

#1812

#1814

#1815

#1816

#1818

#1819

#182

#1820

#1821

#1821

#1825

#1827

#1828

#1829

#183

#183

#1830

#1835

#1837

#1838

#184

#184

#1840

#1841

#1845

#1845

#1846

#1849

#185

#1851

#1852

#1853

#1854

#1857

#1859

#186

#186

#1860

#1862

#1865

#1866

#1868

#187

#187

#1872

#1873

#1880

#1882

#1887

#1887

#1892

#1892

#1894

#1894

#19

#19

#190

#190

#1901

#1901

#1905

#191

#191

#1914

#1915

#1916

#1919

#192

#1926

#1929

#193

#1935

#1935

#1936

#194

#1940

#1941

#1942

#1942

#1944

#1944

#1947

#1949

#1950

#1952

#1954

#1955

#1959

#1959

#1964

#1965

#1966

#1967

#1969

#1973

#1974

#1975

#1975

#1976

#1977

#1979

#198

#1980

#1984

#1986

#1988

#199

#1990

#1991

#1992

#1992

#1995

#1997

#1997

#1999

#200

#200

#2014

#2015

#2015

#2019

#202

#2020

#2020

#2026

#2026

#204

#205

#205

#207

#208

#208

#21

#211

#213

#214

#215

#216

#216

#217

#218

#219

#22

#221

#222

#222

#223

#228

#229

#230

#231

#233

#234

#235

#236

#237

#239

#24

#241

#242

#242

#243

#244

#245

#246

#248

#25

#250

#251

#251

#252

#253

#254

#258

#259

#26

#260

#261

#262

#264

#265

#266

#267

#269

#27

#271

#272

#272

#274

#277

#278

#279

#28

#280

#281

#282

#283

#284

#285

#285

#287

#288

#289

#29

#291

#294

#295

#296

#298

#298

#299

#3

#30

#300

#301

#302

#303

#305

#307

#308

#309

#31

#310

#311

#312

#313

#314

#315

#316

#318

#321

#322

#323

#323

#325

#325

#326

#326

#327

#329

#330

#332

#333

#334

#336

#338

#339

#340

#343

#344

#345

#346

#346

#347

#348

#349

#350

#351

#352

#353

#354

#355

#356

#358

#359

#360

#361

#362

#363

#364

#365

#366

#367

#368

#369

#370

#371

#372

#373

#375

#376

#377

#378

#379

#38

#380

#382

#384

#386

#386

#387

#388

#389

#39

#390

#392

#395

#395

#396

#397

#398

#399

#4

#40

#400

#401

#402

#404

#407

#409

#41

#410

#411

#412

#413

#416

#417

#419

#419

#42

#420

#421

#425

#425

#427

#428

#429

#430

#433

#434

#435

#436

#437

#438

#439

#44

#440

#443

#444

#445

#447

#448

#448

#449

#45

#450

#451

#452

#453

#454

#456

#458

#458

#46

#460

#461

#462

#464

#465

#467

#468

#469

#470

#471

#472

#472

#475

#477

#477

#479

#481

#482

#483

#484

#485

#487

#488

#489

#490

#490

#492

#493

#493

#494

#495

#496

#497

#5

#50

#501

#504

#506

#507

#509

#509

#51

#512

#513

#514

#514

#516

#517

#518

#519

#52

#522

#523

#524

#525

#526

#527

#528

#529

#530

#530

#531

#532

#532

#533

#536

#537

#538

#539

#539

#54

#54

#540

#541

#542

#544

#545

#545

#546

#549

#55

#550

#551

#551

#552

#553

#554

#555

#558

#560

#560

#561

#562

#562

#563

#563

#564

#565

#565

#567

#568

#57

#571

#572

#573

#573

#574

#575

#58

#583

#584

#586

#588

#588

#591

#593

#595

#595

#597

#598

#6

#60

#601

#601

#604

#606

#609

#611

#612

#613

#614

#615

#617

#618

#619

#62

#621

#622

#623

#624

#624

#625

#627

#628

#629

#63

#63

#630

#631

#632

#635

#638

#639

#64

#640

#642

#645

#647

#648

#649

#65

#650

#653

#654

#656

#657

#659

#660

#662

#663

#663

#665

#668

#669

#670

#672

#675

#676

#678

#679

#679

#680

#681

#683

#686

#687

#688

#690

#691

#692

#693

#696

#698

#7

#700

#701

#704

#705

#706

#71

#717

#719

#72

#72

#720

#721

#721

#722

#725

#726

#727

#728

#729

#729

#73

#730

#731

#732

#732

#735

#737

#738

#742

#745

#745

#746

#75

#750

#751

#752

#753

#755

#758

#76

#762

#765

#768

#77

#773

#774

#778

#78

#782

#782

#783

#784

#787

#789

#79

#790

#791

#792

#795

#796

#797

#798

#799

#799

#8

#8

#80

#801

#804

#806

#808

#808

#81

#81

#812

#813

#815

#82

#820

#821

#822

#823

#824

#827

#828

#829

#829

#83

#830

#831

#832

#833

#835

#838

#84

#843

#844

#848

#849

#85

#852

#854

#856

#858

#86

#86

#861

#862

#863

#865

#868

#868

#869

#87

#870

#871

#874

#874

#875

#876

#879

#880

#881

#882

#883

#884

#888

#89

#890

#891

#892

#893

#894

#895

#897

#898

#9

#90

#900

#901

#902

#903

#904

#904

#905

#906

#907

#907

#908

#91

#91

#912

#913

#914

#915

#916

#919

#927

#933

#933

#934

#936

#937

#94

#941

#942

#943

#944

#945

#947

#949

#95

#95

#950

#950

#953

#954

#958

#958

#96

#961

#961

#962

#965

#967

#968

#969

#970

#971

#972

#974

#975

#976

#977

#98

#980

#981

#982

#983

#984

#985

#986

#988

#990

#992

#992

#993

#994

#995

#996

#997

v0.1

v1.0

v1.1

Mono Color

• a2a79c7992 Add function display_and_save_batch in egs/wenetspeech/ASR/pruned_transducer_stateless2/train.py suxia 2022-08-10 17:59:31 +08:00
• 56afb4aa3c Fix comments pkufool 2022-08-10 17:53:49 +08:00
• 1138b27f16 modify pretrained.py yaozengwei 2022-08-10 17:16:09 +08:00
• 88400a4435 Fix torch.jit.script pkufool 2022-08-10 16:49:35 +08:00
• 8f3645e5cb modify test_model.py, test if the model can be successfully exported by jit.trace yaozengwei 2022-08-10 16:20:25 +08:00
• 89124a59ac Convert make_pad_mask Fangjun Kuang 2022-08-10 16:05:31 +08:00
• 522a45ce75 add using averaged model in export.py yaozengwei 2022-08-10 15:43:50 +08:00
• f51e64dada add cut_id to results for all recipes pkufool 2022-08-10 14:52:12 +08:00
• 317f47fb37 test RelPositionalEncoding Fangjun Kuang 2022-08-09 23:32:28 +08:00
• 6217b5e64c Merge branch 'master' into sort_results pkufool 2022-08-09 22:23:18 +08:00
• 10360bed41 Test encoder_embed Fangjun Kuang 2022-08-09 20:03:38 +08:00
• 45c7894111 support jit trace yaozengwei 2022-08-09 19:29:21 +08:00
• 5149788cb2
  Fix computing averaged loss in the aishell recipe. (#523) Fangjun Kuang 2022-08-09 10:53:31 +08:00
• 365c6aa045 Support converting RelPositionalEncoding. Fangjun Kuang 2022-08-08 15:27:04 +08:00
• 4ec243c730 begin to add documents for pruned_transducer_stateless pkufool 2022-08-08 10:41:13 +08:00
• aa078cc6d7 Add cut_id to recognition results pkufool 2022-08-07 17:19:19 +08:00
• dc6499a052 Merge branch 'master' into sort_results pkufool 2022-08-07 15:41:31 +08:00
• 865fd211f7 Added export.py Guanbo Wang 2022-08-07 04:35:41 +00:00
• b13b20b086 Added decoding scripts Guanbo Wang 2022-08-07 04:34:12 +00:00
• f7c3d1ee28
  Merge 561c428e508da15074afb4b3496f5f6aafbe65d5 into f24b76e64bb59e157e3904d0330a132a308f18c0 Shayne Mei 2022-08-07 12:00:32 +08:00
• b4aa7b0a7e Filter non-finite losses Fangjun Kuang 2022-08-07 06:46:53 +08:00
• f24b76e64b
  fix torchaudio version (#524) FNLPprojects 2022-08-06 18:33:43 +08:00
• 595aabce85 fix torchaudio version xinzhulin 2022-08-06 18:32:30 +08:00
• 21dea66071 fix torchaudio version xinzhulin 2022-08-06 18:04:00 +08:00
• 5c33899ddc Increase cov_min[3] from 0.001 to 0.002 Daniel Povey 2022-08-06 16:28:02 +08:00
• f1a664e0d4 Set find_unused_parameters optionally. Fangjun Kuang 2022-08-06 12:52:25 +08:00
• 540020bdc8 Fix computing averaged loss in the aishell recipe. Fangjun Kuang 2022-08-06 12:25:11 +08:00
• 1f7832b93c
  Fix loading sampler state dict. (#421) Fangjun Kuang 2022-08-06 10:00:08 +08:00
• 9bbf8ada57 Scale up diag of grad_cov by 1.0001 prior to diagonalizing it. Daniel Povey 2022-08-06 07:06:23 +08:00
• c021b4fec6 Increase cov_min[3] from 0.0001 to 0.001 Daniel Povey 2022-08-06 07:02:52 +08:00
• d69d83a83e test conformer.encoder_embed Fangjun Kuang 2022-08-05 21:28:05 +08:00
• 0615fb316f add missing file Fangjun Kuang 2022-08-05 20:49:42 +08:00
• 280e1c0312 Finishing testing encoder_embedding. Fangjun Kuang 2022-08-05 20:35:23 +08:00
• 03b056ca37 add scaling converter for ScaledLSTM yaozengwei 2022-08-05 19:38:30 +08:00
• 9e4b5bdfdf Merge remote-tracking branch 'k2-fsa/master' into lstm yaozengwei 2022-08-05 14:36:04 +08:00
• 4ace4f2ed0 Sort result to make it more convenient to compare decoding results pkufool 2022-08-05 12:22:43 +08:00
• a5b9b7b974 Cosmetic changes Daniel Povey 2022-08-05 03:49:54 +08:00
• 7157f62af3
  Merging onnx models (#518) Yunusemre 2022-08-04 18:03:41 +03:00
• 41b983ba7b fix minor Yunus Emre Özköse 2022-08-04 16:40:00 +03:00
• b406c1beff Test ScaledConv2D. Fangjun Kuang 2022-08-04 21:39:20 +08:00
• 4c3346bf6c revert to previous requirements.txt Yunus Emre Özköse 2022-08-04 15:00:14 +03:00
• a4dd273776
  fix about tensorboard (#516) Zengwei Yao 2022-08-04 19:57:12 +08:00
• a213600065 fix instaliing onnx_graphsurgeon Yunus Emre Özköse 2022-08-04 13:32:22 +03:00
• f291599b4d fix installing onnx_graphsurgeon Yunus Emre Özköse 2022-08-04 12:04:25 +03:00
• 19d5435afc fix input/output names Yunus Emre Özköse 2022-08-04 09:11:21 +03:00
• 40126355ec fix requirements Yunus Emre Özköse 2022-08-04 08:36:00 +03:00
• e538232485
  change for pruned rnnt5 train.py (#519) Mingshuang Luo 2022-08-04 12:29:39 +08:00
• f061cac4f3 Change default ctc loss scale value from 0.5 to 0.3 Fangjun Kuang 2022-08-04 12:06:22 +08:00
• e07adc70a9 change for pruned rnnt5 train.py luomingshuang 2022-08-04 11:51:19 +08:00
• dc9133227f Reworked how inverse is done, fixed bug in _apply_min_max_with_metric, regarding how M is normalized. Daniel Povey 2022-08-04 09:46:14 +08:00
• 18a6b8afad fix style Yunus Emre Özköse 2022-08-03 17:10:28 +03:00
• d2de493cd8 fix style Yunus Emre Özköse 2022-08-03 17:05:16 +03:00
• d382455945 add onnx-all-in-one test Yunus Emre Özköse 2022-08-03 16:50:55 +03:00
• 6d3ad6e9dd remove unused arguments Yunus Emre Özköse 2022-08-03 16:50:21 +03:00
• 390aeca769 minor fix Yunus Emre Özköse 2022-08-03 16:23:51 +03:00
• f3a546e04f add onnx_check script for all-in-one onnx model Yunus Emre Özköse 2022-08-03 15:37:56 +03:00
• 183821e6a0 add export function of onnx-all-in-one to export.py Yunus Emre Özköse 2022-08-03 15:37:23 +03:00
• 36eacaccb2
  Fix preparing char based lang and add multiprocessing for wenetspeech text segmentation (#513) Weiji Zhuang 2022-08-03 19:19:40 +08:00
• 71871d5614 fix style WeijiZhuang 2022-08-03 18:24:07 +08:00
• 6af5a82d8f
  Convert ScaledEmbedding to nn.Embedding for inference. (#517) Fangjun Kuang 2022-08-03 15:34:55 +08:00
• c9bf1f49db fix style yaozengwei 2022-08-03 15:30:08 +08:00
• a7021400c6 Fix CI style issues. Fangjun Kuang 2022-08-03 15:26:05 +08:00
• e130e41b83 Convert ScaledEmbedding to nn.Embedding for inference. Fangjun Kuang 2022-08-03 15:24:57 +08:00
• 16ea305fbf fix metricstracker yaozengwei 2022-08-03 15:14:17 +08:00
• 561c428e50
  Merge branch 'master' into use_explicit_relative_imports Shayne Mei 2022-08-02 22:02:58 -07:00
• 58a96e5b68
  Support exporting to ONNX format (#501) Fangjun Kuang 2022-08-03 10:30:28 +08:00
• ca19b98949 sort imports shaynemei 2022-08-02 17:45:23 -07:00
• 5657fa44a4 use explicit relative imports shaynemei 2022-08-02 17:44:36 -07:00
• 887819cd8a
  Merge 1f843e18f227639444dd8c6ae16d504684d2e452 into 132132f52a660f74dac552b432776d82aa1f5dab Fangjun Kuang 2022-08-02 18:35:58 -04:00
• 766bf69a98 Reduce cov_max[2] from 4.0 to 3.5 Daniel Povey 2022-08-03 04:10:11 +08:00
• fffd3bbd9e Fix preparing char based lang for wenetspeech WeijiZhuang 2022-08-02 23:40:27 +08:00
• b986ef5ddc add multiprocessing for wenetspeech text segmentation WeijiZhuang 2022-08-02 23:38:41 +08:00
• 5c2c91e53f fix Guanbo Wang 2022-08-02 15:38:39 +00:00
• 132132f52a
  liear_fst_with_self_loops (#512) LIyong.Guo 2022-08-02 22:28:12 +08:00
• 0fbaa0d32f liear_fst_with_self_loops Guo Liyong 2022-08-02 21:34:22 +08:00
• 72dc1780d6 Fix as_strided for streaming conformer. Fangjun Kuang 2022-08-02 20:39:55 +08:00
• 129b28aa9b Increase cov_min[2] from 0.05 to 0.1; decrease cov_max[2] from 5.0 to 4.0. Daniel Povey 2022-08-02 15:17:24 +08:00
• 202752418a Increase cov_min[2] from 0.02 to 0.05. Daniel Povey 2022-08-02 15:15:41 +08:00
• e44ab25e99 Bug fix Daniel Povey 2022-08-02 14:31:37 +08:00
• 10846568b9 use explicit relative imports for librispeech shaynemei 2022-08-01 21:39:21 -07:00
• 8714df792a use explicit relative imports for aimeeting shaynemei 2022-08-01 21:39:09 -07:00
• 6df69603a8 use explicit relative imports for aishell4 shaynemei 2022-08-01 21:37:24 -07:00
• 4cb62a3202 use explicit relative imports for aishell2 shaynemei 2022-08-01 21:35:06 -07:00
• 51f2e377ba use explicit relative imports for aishell shaynemei 2022-08-01 21:34:58 -07:00
• dd25072b3b use explicit relative imports for aidatatang_200zh shaynemei 2022-08-01 21:34:31 -07:00
• 2d85fd103d use explicit relative imports shaynemei 2022-08-01 21:24:16 -07:00
• e9f4ada1c0 Swap the order of applying min and max in smoothing operations Daniel Povey 2022-08-02 11:55:43 +08:00
• 7daf148342 use explicit relative imports for aidatatang_200zh shaynemei 2022-08-01 20:54:59 -07:00
• 60621b242a sort imports shaynemei 2022-08-01 20:49:52 -07:00
• 9149a92dd8 use explicit relative imports shaynemei 2022-08-01 20:46:10 -07:00
• e7b5a8ecbb sort imports shaynemei 2022-08-01 20:37:16 -07:00
• 9473c7e23d Lots of changes to how min and max are applied, use 1-norm for min in smooth_cov but not _apply_min_max_with_metric. Daniel Povey 2022-08-02 11:29:54 +08:00
• f2b72c80ff flake8 Guanbo Wang 2022-08-02 02:20:13 +00:00
• 9701cf081c more links Guanbo Wang 2022-08-02 02:14:31 +00:00
• 71dea95287 Added train.py Guanbo Wang 2022-08-02 02:04:04 +00:00
• 6ab4cf615d 1st draft of new method of normalizing covs that uses normalization w.r.t. spectral 2-norm Daniel Povey 2022-08-02 09:34:37 +08:00
• 10aaa1ffd1 link the files from librispeech/ASRpruned_transducer_stateless5 Guanbo Wang 2022-08-02 01:24:34 +00:00
• 4919134a94 Merge making hidden_dim an arg Daniel Povey 2022-08-02 09:09:29 +08:00
• c64bd5ebcd Merge making hidden_dim an arg Daniel Povey 2022-08-02 09:07:36 +08:00
• b008340d83 Merge making hidden_dim an arg Daniel Povey 2022-08-02 09:01:19 +08:00