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

#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

#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

#2026

#2027

#204

#2045

#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

#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

• b0bce20e21 Modify subsampling.py to make T'=T//4 strictly yaozengwei 2022-04-02 16:26:13 +08:00
• 022b0f3c55 Modify icefall/__init__.py. (#287) Zengwei Yao 2022-04-02 15:01:45 +08:00
• 2545237eb3 Changing initial_speed from 0.25 to 01 Daniel Povey 2022-04-05 18:00:54 +08:00
• 25724b5ce9 Bug-fix RE sign of target_rms Daniel Povey 2022-04-05 13:49:35 +08:00
• d1a669162c Fix bug in lambda Daniel Povey 2022-04-05 13:31:52 +08:00
• ed8eba91e1 Reduce model_warm_step from 4k to 3k Daniel Povey 2022-04-05 13:24:09 +08:00
• c3169222ae Simplified optimizer, rework somet things.. Daniel Povey 2022-04-05 13:23:02 +08:00
• 0f5957394b Fix to reading scheudler from optim Daniel Povey 2022-04-05 12:58:43 +08:00
• 1548cc7462 Fix checkpoint-writing Daniel Povey 2022-04-05 11:19:40 +08:00
• cb3ba16f2b
  Fix aishell prepare.sh when using pre-download data (#291) Wei Kang 2022-04-05 10:22:49 +08:00
• 34c380cd8b For older pytorch version pkufool 2022-04-05 07:50:52 +08:00
• 131fbafa61 Fix aishell prepare.sh when using pre-download data pkufool 2022-04-05 07:33:03 +08:00
• 47d49f29d7 Fix weight decay formula by adding 1/1-beta Daniel Povey 2022-04-05 00:31:55 +08:00
• 2b0727a355 Fix weight decay formula by adding 1/1-beta Daniel Povey 2022-04-05 00:31:28 +08:00
• 234366e51c Fix type of parameter Daniel Povey 2022-04-05 00:18:36 +08:00
• 179d0605ea Change initialization to 0.25 Daniel Povey 2022-04-04 23:34:39 +08:00
• d1f2f93460 Some fixes.. Daniel Povey 2022-04-04 22:40:18 +08:00
• 72f4a673b1 First draft of new approach to learning rates + init Daniel Povey 2022-04-04 20:21:34 +08:00
• 4929e4cf32 Change how warm-step is set Daniel Povey 2022-04-04 17:09:25 +08:00
• a5bbcd7b71 Make training more efficient, avoid redoing some projections. Daniel Povey 2022-04-04 14:10:38 +08:00
• 99e9d6c4b8 Some cleanups Daniel Povey 2022-04-04 13:37:10 +08:00
• 0fd0828f79 Fix to joiner to allow different dims Daniel Povey 2022-04-04 13:34:43 +08:00
• 87cf9231ea
  Support specifying iteration number of checkpoints for decoding. (#289) Fangjun Kuang 2022-04-03 13:02:08 +08:00
• 00a84e2de5 Support specifying iteration number of checkpoints for decoding. Fangjun Kuang 2022-04-03 12:55:10 +08:00
• 29d186118f Exclude loss calculation from mix precision training pkufool 2022-04-03 07:59:17 +08:00
• 9f62a0296c Revert transducer_stateless/ to state in upstream/master Daniel Povey 2022-04-02 21:16:39 +08:00
• 807fcada68 Change learning speed of simple_lm_proj Daniel Povey 2022-04-02 20:15:11 +08:00
• 34500afc43 Various bug fixes Daniel Povey 2022-04-02 20:06:43 +08:00
• 8be10d3d6c First draft of model rework Daniel Povey 2022-04-02 20:03:21 +08:00
• eec597fdd5 Merge changes from master Daniel Povey 2022-04-02 18:43:42 +08:00
• e0ba4ef3ec Make layer dropout rate 0.075, was 0.1. Daniel Povey 2022-04-02 17:47:12 +08:00
• 0b6a2213c3
  Modify icefall/__init__.py. (#287) Zengwei Yao 2022-04-02 15:01:45 +08:00
• 189ca555b1
  Use Emformer as RNN-T encoder. (#278) Fangjun Kuang 2022-04-02 13:37:39 +08:00
• bc9a82b518 Modify icefall/__init__.py and .flake8. yaozengwei 2022-04-02 10:34:06 +08:00
• 00baebd46e Modify icefall/__init__.py to import common functions defined in icefall/utils.py. yaozengwei 2022-04-01 22:33:15 +08:00
• 128c9db545 Add RNN-T Emformer for Aishell. Fangjun Kuang 2022-04-01 21:58:40 +08:00
• 3479af0e6e Minor fixes. Fangjun Kuang 2022-04-01 19:46:52 +08:00
• 45f872c27d Remove final dropout Daniel Povey 2022-04-01 19:33:20 +08:00
• 6f64a0ed8d Support streaming decoding. Fangjun Kuang 2022-04-01 19:07:34 +08:00
• 92ec2e356e Fix test-mode Daniel Povey 2022-04-01 12:22:12 +08:00
• 397216eb78 Merge branch 'master' of https://github.com/k2-fsa/icefall into spgi Desh Raj 2022-03-31 14:55:33 -04:00
• e7493ede90
  Don't use a lambda for dataloader's worker_init_fn. (#284) Fangjun Kuang 2022-03-31 20:32:00 +08:00
• 4f87802200 Fixes after comment. Fangjun Kuang 2022-03-31 20:29:40 +08:00
• 9e5ca821bc Don't use a lambda for dataloader's worker_init_fn. Fangjun Kuang 2022-03-31 20:22:18 +08:00
• feb526c2a4 Predicting blanks via gradients from the trivial joiner. Fangjun Kuang 2022-03-31 20:12:41 +08:00
• 2ff81b2838 support half precision training pkufool 2022-03-31 19:58:57 +08:00
• 239a8fa1f2 Copy files for editing. Fangjun Kuang 2022-03-31 16:54:58 +08:00
• 8caa18e2fe Bug fix to warmup_scale Daniel Povey 2022-03-31 17:30:51 +08:00
• e7d369ab29 Copy files. Fangjun Kuang 2022-03-31 16:51:27 +08:00
• 9a11808ed3
  Set the seed for dataloader. (#282) Fangjun Kuang 2022-03-31 16:48:46 +08:00
• 49bc761ba1 Merge branch 'rework2i_restoredrop_scaled_warmup' into rework2i_restoredrop_scaled_warmup_2proj Daniel Povey 2022-03-31 14:45:55 +08:00
• e663713258 Change how warmup is applied. Daniel Povey 2022-03-31 14:43:49 +08:00
• fcb0dba2cf Reduce initial_speed from 0.5 to 0.25 Daniel Povey 2022-03-31 13:47:28 +08:00
• 025d690995 Reduce initial_speed further from 0.5 to 0.25 Daniel Povey 2022-03-31 13:39:56 +08:00
• ec54fa85cc Use initial_speed=0.5 Daniel Povey 2022-03-31 13:04:09 +08:00
• e59db01b7c Reduce initial_speed Daniel Povey 2022-03-31 13:03:26 +08:00
• c67ae0f3a1 Make 2 projections.. Daniel Povey 2022-03-31 13:02:40 +08:00
• f75d40c725 Replace nn.Linear with ScaledLinear in simple joiner Daniel Povey 2022-03-31 12:18:31 +08:00
• 9a0c2e7fee Merge branch 'rework2i' into rework2i_restoredrop Daniel Povey 2022-03-31 12:17:02 +08:00
• f47fe8337a Remove some un-used code Daniel Povey 2022-03-31 12:16:08 +08:00
• 65a2275312 Set the seed for dataloader. Fangjun Kuang 2022-03-31 12:09:03 +08:00
• 0599f38281 Add final dropout to conformer Daniel Povey 2022-03-31 11:53:54 +08:00
• fc40bfea82
  fix typo of torch.eig (#281) LIyong.Guo 2022-03-31 10:43:46 +08:00
• 2045125fd9
  Fix CI. (#280) Fangjun Kuang 2022-03-31 10:43:02 +08:00
• 07a9a3410d Minor fixes. Fangjun Kuang 2022-03-31 10:27:58 +08:00
• d368a69e3f fix typo of torch.eig glynpu 2022-03-30 23:09:56 +08:00
• a2aca9f643 Bug-fix Daniel Povey 2022-03-30 21:42:15 +08:00
• f87811e65c Fix RE identity Daniel Povey 2022-03-30 21:41:46 +08:00
• 709c387ce6 Initial refactoring to remove unnecessary vocab_size Daniel Povey 2022-03-30 21:40:22 +08:00
• f284ae6d81 Fix CI. Fangjun Kuang 2022-03-30 18:58:39 +08:00
• 981b064007
  Update doc to clarify the installation order of dependencies. (#279) Fangjun Kuang 2022-03-30 18:50:54 +08:00
• cb9271a3e2 Update doc to clarify the installation order of dependencies. Fangjun Kuang 2022-03-30 18:49:35 +08:00
• 5728a4456e Use Emformer model as RNN-T encoder. Fangjun Kuang 2022-03-30 17:09:15 +08:00
• e867a62d32 Copy files. Fangjun Kuang 2022-03-30 16:09:51 +08:00
• b4c7a27f3c Add emformer model. Fangjun Kuang 2022-03-30 16:09:32 +08:00
• f686635b54
  Update diagnostics (#260) Mingshuang Luo 2022-03-30 14:52:55 +08:00
• 4b5b49c9b0 Add log weight pushing pkufool 2022-03-30 12:58:26 +08:00
• 74121ac478 Merge branch 'rework2h_randloader_pow0.333_conv_8' into rework2h_randloader_pow0.333_conv_8_lessdrop_speed Daniel Povey 2022-03-30 12:24:15 +08:00
• 37ab0bcfa5 Reduce speed of some components Daniel Povey 2022-03-30 11:46:23 +08:00
• 7c46c3b0d4 Remove dropout in output layer Daniel Povey 2022-03-30 11:20:04 +08:00
• 21a099b110 Fix padding bug Daniel Povey 2022-03-30 11:18:04 +08:00
• ca6337b78a Add another convolutional layer Daniel Povey 2022-03-30 11:11:32 +08:00
• 8bb2f01b11 Add LG decoding pkufool 2022-03-30 10:52:47 +08:00
• 1b8d7defd0 Reduce 1st conv channels from 64 to 32 Daniel Povey 2022-03-30 00:44:18 +08:00
• 4e453a4bf9 Rework conformer, remove some code. Daniel Povey 2022-03-29 23:41:13 +08:00
• 11124b03ea Refactoring and simplifying conformer and frontend Daniel Povey 2022-03-29 20:32:14 +08:00
• 57f943b25c Merge branch 'rework2h_randloader' into rework2h_pow0.333 Daniel Povey 2022-03-29 19:05:39 +08:00
• 7c5249fb88 Minor fixes. Fangjun Kuang 2022-03-29 16:10:19 +08:00
• 0aa7bf08b8
  Merge branch 'master' into wenetspeech-pruned-transducer-stateless-pinyin Mingshuang Luo 2022-03-28 21:49:21 +08:00
• 5fa6c67873 do a change for .flake8 luomingshuang 2022-03-28 21:48:35 +08:00
• e53411c99e pruned_transducer_stateless_for_wenetspeech luomingshuang 2022-03-28 21:18:33 +08:00
• 52f1f6775d Update beam search to support max/log_add in selecting duplicate hyps. Fangjun Kuang 2022-03-28 12:33:58 +08:00
• ce079e1417 Add results for standard beam search. Fangjun Kuang 2022-03-27 23:46:50 +08:00
• 2cde99509f Change max-keep-prob to 0.95 Daniel Povey 2022-03-27 23:21:42 +08:00
• cc6c608fb6 Minor fixes. Fangjun Kuang 2022-03-27 21:50:56 +08:00
• 58794ba493 Add results. Fangjun Kuang 2022-03-27 21:35:21 +08:00
• b0d34fbb8c Update results for stateless transducer without pruned RNN-T loss. Fangjun Kuang 2022-03-27 16:16:08 +08:00
• 262388134d Increase model_warm_step to 4k Daniel Povey 2022-03-27 11:18:16 +08:00
• 8a8134b9e5 Change power of lr-schedule from -0.5 to -0.333 Daniel Povey 2022-03-17 13:18:58 +08:00
• 953aecf5e3 Reduce layer-drop prob after warmup to 1 in 100 Daniel Povey 2022-03-27 00:25:32 +08:00