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

#202

#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

• 082a890635 Fix apply_prob_decay to 500 Daniel Povey 2022-06-09 19:20:03 +08:00
• fca844d80c Make it really have 2k decay and revert to 0.02 scale Daniel Povey 2022-06-09 17:45:11 +08:00
• 391cb707fd do some changes luomingshuang 2022-06-09 14:22:21 +08:00
• e99344f15e Increase scale to 0.04 Daniel Povey 2022-06-09 13:24:31 +08:00
• 734d97c47b remane streaming_feature_extractor.py yaozengwei 2022-06-09 13:05:06 +08:00
• acc8a36b5e refactor Stream class yaozengwei 2022-06-09 13:00:22 +08:00
• 02eb6b210b add english abbreviations into tokens and finetune the model based on pretrained model luomingshuang 2022-06-09 12:29:29 +08:00
• bfcd288afd Decrease scale on decorrelate component from 0.02 to 0.01 Daniel Povey 2022-06-09 12:07:19 +08:00
• 56d6dd55ae Bug fixes Daniel Povey 2022-06-09 12:06:35 +08:00
• dbda1644b5
  Replace load_manifest_lazy with load_manifest for MUSAN. (#412) Fangjun Kuang 2022-06-09 11:42:18 +08:00
• 9921165619 Replace load_manifest_lazy with load_manifest for MUSAN. Fangjun Kuang 2022-06-09 11:32:57 +08:00
• 1669e21c0c Use decorrelation in conformer layers also Daniel Povey 2022-06-09 00:05:49 +08:00
• ed66877694
  Replace ChunkedLilcomHdf5Writer with LilcomChunkyWriter. (#411) Fangjun Kuang 2022-06-09 11:18:52 +08:00
• c67dd6c104 Replace ChunkedLilcomHdf5Writer with LilcomChunkyWriter. Fangjun Kuang 2022-06-09 11:14:43 +08:00
• ea741070e0 Revert to use LilcomChunkyWriter and load_manifest. Fangjun Kuang 2022-06-08 21:13:59 +08:00
• b9a476c7bb Remove loss factor from decorr_loss_scale Daniel Povey 2022-06-08 20:19:17 +08:00
• 8512aaf585
  fix typos (#409) Quandwang 2022-06-08 20:08:44 +08:00
• 8e56445c70 Try to resolve graph-freed problem Daniel Povey 2022-06-08 20:07:35 +08:00
• e4ce1e20a3 fix typos Quandwang 2022-06-08 19:57:00 +08:00
• 46ca1cd4c4 Add Decorrelate module that adds something to gradients in backward pass Daniel Povey 2022-06-08 19:44:58 +08:00
• 9fb8645168 Implement JoinDropout Daniel Povey 2022-06-08 16:11:48 +08:00
• c8cb425e51 combine the training data and decode without webdataset luomingshuang 2022-06-08 15:35:53 +08:00
• 5079d99ee2
  a correction for text2segmentation.py (#407) Mingshuang Luo 2022-06-08 12:06:57 +08:00
• e6f145a06a a correction for text2segmentation.py luomingshuang 2022-06-08 12:00:33 +08:00
• e7886d49a9 Bug fix Daniel Povey 2022-06-08 11:05:29 +08:00
• a83bde1372 Simplify implementation as current idea was not working to decorrelate Daniel Povey 2022-06-08 10:24:41 +08:00
• 135be1e19c Change dropout_rate from 0.2 to 0.1; fix logging statement; fix assignment to rand_scales, nonrand_scales to use [:] Daniel Povey 2022-06-08 00:42:04 +08:00
• f8071e9373 modify emformer states stack and unstack, streaming decoding, to be continued yaozengwei 2022-06-07 23:57:20 +08:00
• a6050cb2de Implement new, more principled but maybe slower version. Daniel Povey 2022-06-07 23:38:38 +08:00
• 296303abdc add text normalize luomingshuang 2022-06-07 22:36:20 +08:00
• 4c2cbff501 do some changes luomingshuang 2022-06-07 22:30:50 +08:00
• 75c822c7e9 Pre and post-multiply by inv_sqrt_stddev,stddev Daniel Povey 2022-06-07 20:32:18 +08:00
• a270973b69 Add gaussian version of decorrelation Daniel Povey 2022-06-07 18:55:48 +08:00
• 5d24489752 Have 2 scales on dropout Daniel Povey 2022-06-07 18:26:23 +08:00
• 1094a3cb37
  Replace LilcomChunkyWriter with ChunkedLilcomHdf5Writer. (#404) Fangjun Kuang 2022-06-07 18:14:25 +08:00
• 87a355e376 Replace LilcomChunkyWriter with ChunkedLilcomHdf5Writer. Fangjun Kuang 2022-06-07 17:40:05 +08:00
• 53ca61db7a Reduce scale on decorrelation by 5, to 0.01 Daniel Povey 2022-06-07 17:10:54 +08:00
• 7c6d923d3f Add decorrelation to joiner Daniel Povey 2022-06-07 16:47:54 +08:00
• cd6b707e2b Various bug fixes Daniel Povey 2022-06-07 16:45:32 +08:00
• aebe9c22dd Minor fixes pkufool 2022-06-07 15:59:58 +08:00
• b4b3a848ed Merge branch 'master' into icefall-pruned-rnnt5-aishell4 luomingshuang 2022-06-07 12:20:12 +08:00
• ddc55423b1 do some changes and text normalize luomingshuang 2022-06-07 12:16:51 +08:00
• d7be9bd9c5 Minor fixes pkufool 2022-06-07 12:00:26 +08:00
• 40a0934b4e Implement GaussProjDrop Daniel Povey 2022-06-07 11:51:24 +08:00
• 80c46f0abd
  Fix exporting emformer with torchscript using torch 1.6.0 (#402) Fangjun Kuang 2022-06-07 09:19:37 +08:00
• 5df1406684 copy from streaming branch yaozengwei 2022-06-06 21:51:47 +08:00
• 124ad1db8b copy from streaming branch yaozengwei 2022-06-06 21:20:55 +08:00
• 13899dff51 refactor, use fixed-length cache for batch decoding yaozengwei 2022-06-06 21:19:25 +08:00
• 1c794e32b0 Minor fixes pkufool 2022-06-06 20:19:49 +08:00
• 888f526234 Fix exporting emformer with torchscript using torch 1.6.0 Fangjun Kuang 2022-06-06 20:13:08 +08:00
• 09b0c54983 Minor fixes pkufool 2022-06-06 17:56:22 +08:00
• 4352a16f57 Fix bug that relates to modifying U in place Daniel Povey 2022-06-06 17:43:15 +08:00
• 29fa878fff
  Fix Emformer for torchscript using torch 1.6.0 (#401) Fangjun Kuang 2022-06-06 17:08:07 +08:00
• a364837e91 Fix Emformer for torchscript using torch 1.6.0 Fangjun Kuang 2022-06-06 17:06:36 +08:00
• 31848dcd11 Randomize the projections Daniel Povey 2022-06-06 16:05:18 +08:00
• 0a21eaae7f
  do a change for decode.py (#400) Mingshuang Luo 2022-06-06 15:44:04 +08:00
• 6fdb356315 Bug fix RE GPU device Daniel Povey 2022-06-06 15:40:20 +08:00
• 71e927411a Implement FixedProjDrop Daniel Povey 2022-06-06 15:38:59 +08:00
• 6e602d753d do a change for decode.py luomingshuang 2022-06-06 15:35:16 +08:00
• f1abce72f8
  Use jsonl for CutSet in the LibriSpeech recipe. (#397) Fangjun Kuang 2022-06-06 10:19:16 +08:00
• f0d5d731b9 Fix style issues. Fangjun Kuang 2022-06-06 10:04:08 +08:00
• 3aacf75652 fix relative positional encoding in streaming decoding for compution saving pkufool 2022-06-06 06:46:40 +08:00
• 1235e23fbf Minor fixes. Fangjun Kuang 2022-06-05 23:44:58 +08:00
• 28df3ba43f Fix bug re half precision Daniel Povey 2022-06-05 23:26:59 +08:00
• d76aedb790 Make it work for half Daniel Povey 2022-06-05 23:25:51 +08:00
• e535887abb Bug fixes. Daniel Povey 2022-06-05 23:24:02 +08:00
• 136ffb0597 Add ProjDrop for axis-independent dropout Daniel Povey 2022-06-05 22:59:10 +08:00
• accf0afb45 Remove force=True from logging to support Python < 3.8 Fangjun Kuang 2022-06-05 22:38:46 +08:00
• 113818fd00 More fixes to use lazy CutSet. Fangjun Kuang 2022-06-05 22:23:32 +08:00
• 0040ff2157 Merge remote-tracking branch 'dan/master' into jsonl Fangjun Kuang 2022-06-05 21:30:47 +08:00
• b3707d0c3d Use lazy cutset for all recipes. Fangjun Kuang 2022-06-05 21:29:06 +08:00
• 4215ec434a pruned-transducer-stateless5 recipe for aishell4 luomingshuang 2022-06-05 19:53:37 +08:00
• b0e565a253 pruned-transducer-stateless5 recipe for aishell4 luomingshuang 2022-06-05 19:38:10 +08:00
• e5884f82e0
  [Ready to merge] Add prefix for compute fbank (#398) Mingshuang Luo 2022-06-05 18:17:52 +08:00
• 8508ee98f9 add prefix luomingshuang 2022-06-05 18:11:59 +08:00
• 147d29660a add prefix luomingshuang 2022-06-05 18:04:59 +08:00
• d93512344b Use jsonl for cutsets in the librispeech recipe. Fangjun Kuang 2022-06-05 13:10:06 +08:00
• a1ae2f8fa9 Revert some accidental changes Daniel Povey 2022-06-05 11:40:55 +08:00
• 68aa924eeb mgb2 AmirHussein96 2022-06-05 01:00:32 +03:00
• 86e1f9b056 mgb2 AmirHussein96 2022-06-05 00:25:10 +03:00
• b52b5c683f config spec-aug-max-frames-mask-fraction Guo Liyong 2022-06-04 21:05:07 +08:00
• c381b491f1 different weight for masked/unmasked region Guo Liyong 2022-06-04 21:01:07 +08:00
• 8a3068ead8
  Update decode.py (#392) fanlu 2022-06-04 19:08:17 +08:00
• 148f69d8d9
  Update RESULTS.md (#388) Zengwei Yao 2022-06-04 15:52:35 +08:00
• a9a172aa69 Multiply lr by 10; simplify Cain. Daniel Povey 2022-06-04 15:48:33 +08:00
• 494d4f4d74 Merge remote-tracking branch 'k2-fsa/master' into pruned4_result_new yaozengwei 2022-06-04 13:50:07 +08:00
• beab229fd7
  [Ready to merge] Pruned_transducer_stateless2 for alimeeting dataset (#378) Mingshuang Luo 2022-06-04 13:47:46 +08:00
• 0177918f41 fix typos yaozengwei 2022-06-04 13:33:46 +08:00
• 0baf4981d5 update link yaozengwei 2022-06-04 13:17:26 +08:00
• 26b358a9ea add uploaded files links yaozengwei 2022-06-04 13:04:03 +08:00
• ab86e441ce update export.py yaozengwei 2022-06-04 12:51:33 +08:00
• 679972b905 Fix bug; make epsilon work both ways (small+large); increase epsilon to 0.1 Daniel Povey 2022-06-03 19:37:48 +08:00
• 8085ed6ef9 Turn off natural gradient update for biases. Daniel Povey 2022-06-03 18:40:14 +08:00
• 3fff0c75bb Code cleanup Daniel Povey 2022-06-03 11:54:12 +08:00
• d6e65a0e7f Remove decompose=True Daniel Povey 2022-06-03 11:03:18 +08:00
• fce5e36cb0 fix modified_beam_search fanlu3 2022-06-02 21:44:18 +08:00
• ffdf161830
  Update decode.py fanlu 2022-06-02 20:56:34 +08:00
• fc54a99a56 Cutting off invalid frames of encoder_embed output pkufool 2022-06-02 14:19:08 +08:00
• a66a0d84d5 Natural gradient, with power -0.5 (halfway; -1 would be NG) Daniel Povey 2022-06-02 14:01:03 +08:00
• b1f6797af1 Remove some rebalancing code that I am now not going to use. Daniel Povey 2022-06-01 22:19:28 +08:00