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

• 9bb0c7988f add random combiner for training deeper model yaozengwei 2022-07-18 11:50:35 +08:00
• 8bd700cff2 fix scale value in scaling.py yaozengwei 2022-07-18 10:33:35 +08:00
• bb1e1e154a Increasing param_pow to 0.6 and decreasing max_lr_factor from 4 to 3. Daniel Povey 2022-07-18 09:06:32 +08:00
• 8db3b48edb Update parameter dependent part of cov more slowly, plus bug fix. Daniel Povey 2022-07-18 05:26:55 +08:00
• 1d036a6a5a Support streaming decoding pkufool 2022-07-18 00:03:51 +08:00
• 3cedbe3678 fix style yaozengwei 2022-07-17 21:40:29 +08:00
• fd261eca3a Merge remote-tracking branch 'k2-fsa/master' into lstm_new yaozengwei 2022-07-17 21:24:56 +08:00
• 1b0d2f3592 modify .flake8 yaozengwei 2022-07-17 21:22:00 +08:00
• c71788ee57 remove add_model_arguments yaozengwei 2022-07-17 21:20:39 +08:00
• 7c00f92abb fix style yaozengwei 2022-07-17 21:17:45 +08:00
• 872d2390d2 link __init__.py yaozengwei 2022-07-17 20:39:46 +08:00
• ce2d817114 pruned2 -> pruned4 yaozengwei 2022-07-17 20:36:20 +08:00
• 125eac8dee flat weights after scaling yaozengwei 2022-07-17 20:35:29 +08:00
• 539a9d75d4 simplified code in ScaledLSTM yaozengwei 2022-07-17 17:07:14 +08:00
• 5c669b7716 modify streaming decoding files yaozengwei 2022-07-17 16:09:24 +08:00
• 822cc78a9c copy streaming decoding files from pruned_transducer_stateless2 yaozengwei 2022-07-17 15:47:43 +08:00
• 4a0dea2aa2 modify decode.py pretrained.py test_model.py train.py yaozengwei 2022-07-17 15:38:53 +08:00
• b1be6ea475 copy from pruned_transducer_stateless2 yaozengwei 2022-07-17 15:37:27 +08:00
• 89bfb6b9c7 link scaling.py pruned_transducer_stateless2 yaozengwei 2022-07-17 15:35:59 +08:00
• 198cf2635c Reduce param_pow from 0.5 to 0.4. Daniel Povey 2022-07-17 15:35:07 +08:00
• d16b9ec15f link from pruned_transducer_stateless2 yaozengwei 2022-07-17 15:32:54 +08:00
• 3857a87b47 Merge branch 'merge_refactor_param_cov_norank1_iter_batch_max4.0_pow0.5_fix2r_lrupdate200_2k_ns' into merge2_refactor_max4.0_pow0.5_200_1k_ma3.0 Daniel Povey 2022-07-17 15:32:43 +08:00
• 074bd7da71 hardcode bidirectional=False yaozengwei 2022-07-17 15:31:25 +08:00
• 2d53f2ef8b add RNN and Conv2dSubsampling classes in lstm.py yaozengwei 2022-07-17 12:59:27 +08:00
• a572eb4e33 Reducing final lr_update_period from 2k to 1k Daniel Povey 2022-07-17 12:56:02 +08:00
• f36ebad618 Remove 2/3 StructuredLinear/StructuredConv1d modules, use linear/conv1d Daniel Povey 2022-07-17 04:24:48 +08:00
• 7e88e2a0e9 Increase debug freq; add type to diagnostics and increase precision of mean,rms Daniel Povey 2022-07-17 04:41:53 +08:00
• 7c9fcfa5c9 add RNNEncoderLayer and RNNEncoder classes in lstm.py yaozengwei 2022-07-16 22:50:42 +08:00
• 9165de5f57 add ScaledLSTM yaozengwei 2022-07-16 22:47:05 +08:00
• 1ebf714fb7 remove hlg related modifications Guo Liyong 2022-07-16 13:37:31 +08:00
• 604daca1fd Use CTC loss as an auxiliary loss for transducer training. Fangjun Kuang 2022-07-16 08:52:44 +08:00
• de1fd91435 Adding max_abs=3.0 to ActivationBalancer modules inside feedoforward modules. Daniel Povey 2022-07-16 07:19:26 +08:00
• 23e6d2e6d8 Fix to the fix Daniel Povey 2022-07-16 06:53:44 +08:00
• 473efcd531 add self loop to L Guo Liyong 2022-07-16 01:19:04 +08:00
• 4c8d77d14a Fix return type Daniel Povey 2022-07-15 14:18:07 +08:00
• 79d1316905 Add RNN-LM rescoring Erwan 2022-07-12 09:01:39 +02:00
• ffca1ae7fb
  [WIP] Rnn-T LM nbest rescoring (#471) ezerhouni 2022-07-15 04:32:54 +02:00
• 68c5935691 Fix bug re param_cov freshness, properly. Daniel Povey 2022-07-15 08:33:10 +08:00
• b6ee698278 Make LR update period less frequent later in training; fix bug with param_cov freshness, was too fresh Daniel Povey 2022-07-15 07:59:30 +08:00
• 0ce4c654f9 Add temperature in prefix Erwan 2022-07-14 15:16:49 +02:00
• c17233eca7
  [Ready] [Recipes] add aishell2 (#465) Yuekai Zhang 2022-07-14 14:46:56 +08:00
• 42eaaf7c86 change context-size 2 default Yuekai Zhang 2022-07-14 06:42:07 +00:00
• 689441b237 Reduce param_pow from 0.75 to 0.5 Daniel Povey 2022-07-14 06:08:06 +08:00
• 7f6fe02db9 Fix formula for smoothing (was applying more smoothing than intended, and in the opposite sense to intended), also revert max_rms from 2.0 to 4.0 Daniel Povey 2022-07-14 06:06:02 +08:00
• 0a99ceb6ba psd algorithm Guo Liyong 2022-07-14 00:01:28 +08:00
• dfff69b160 update result Yuekai Zhang 2022-07-13 14:10:42 +00:00
• f8d28f0998
  update multi_quantization installation (#469) LIyong.Guo 2022-07-13 21:16:45 +08:00
• d0c171d8a6
  Update egs/librispeech/ASR/pruned_transducer_stateless6/train.py LIyong.Guo 2022-07-13 21:03:06 +08:00
• 3016440035 add more decoding methods Yuekai Zhang 2022-07-13 02:21:47 +00:00
• 4785245e5c Reduce debug freq Daniel Povey 2022-07-13 06:51:23 +08:00
• d48fe0b99c Change max rms from 10.0 to 4.0 Daniel Povey 2022-07-13 05:53:35 +08:00
• bc2882ddcc
  Simplified memory bank for Emformer (#440) Zengwei Yao 2022-07-12 19:19:58 +08:00
• 1a44724c26 fix error in RESULTS.md yaozengwei 2022-07-12 19:12:50 +08:00
• 0fcdd15fec
  Merge branch 'k2-fsa:master' into master Zengwei Yao 2022-07-12 15:39:04 +08:00
• cedfb5a377 Make max eig ratio 10 Daniel Povey 2022-07-12 13:59:58 +08:00
• 2e619be9b0 fix decoding comment Yuekai Zhang 2022-07-12 02:40:51 +00:00
• 13067dddb1 update hf link Yuekai Zhang 2022-07-12 02:13:36 +00:00
• 278358bb9f Remove debug code Daniel Povey 2022-07-12 08:39:14 +08:00
• 8c44ff26f7 Fix bug in batching code for scalars Daniel Povey 2022-07-12 08:36:45 +08:00
• 25cb8308d5 Add max_block_size=512 to PrAdam Daniel Povey 2022-07-12 08:35:14 +08:00
• 41df045773 Simplify formula, getting rid of scalar_exp_avg_sq Daniel Povey 2022-07-11 17:14:12 -07:00
• 4f0e219523 Bug fix to reproduce past results with max_block_size unset. Daniel Povey 2022-07-11 17:03:32 -07:00
• 075a2e27d8 Replace max_fullcov_size with max_block_size Daniel Povey 2022-07-11 16:37:01 -07:00
• 3468c3aa5a Remove ActivationBalancer, unnecessary Daniel Povey 2022-07-11 14:12:24 -07:00
• 7993c84cd6 Apparently working version, with changed test-code topology Daniel Povey 2022-07-11 13:17:29 -07:00
• a2b54cca10 update result Yuekai Zhang 2022-07-11 14:35:39 +00:00
• e5cadba145 Add temperature in doc Erwan 2022-07-11 15:13:46 +02:00
• fd4deeab95 Add fast_beam_search_with_nbest_rescoring in decode Erwan 2022-07-07 15:20:01 +02:00
• 2456307acb Add fast_beam_search_nbest Erwan 2022-07-07 15:11:20 +02:00
• ce26495238
  Rand combine update result (#467) Zengwei Yao 2022-07-11 18:13:31 +08:00
• 245d39b1bb Still debugging but close to done Daniel Povey 2022-07-11 00:33:37 -07:00
• 27da50a1f6 Committing partial work.. Daniel Povey 2022-07-10 15:46:32 -07:00
• d25df4af5e Slight refactoring, preparing for batching. Daniel Povey 2022-07-09 22:24:36 -07:00
• d9a6180ae0 Bug fix Daniel Povey 2022-07-10 10:20:39 +08:00
• b7035844a2 Introduce scalar_max, stop eps getting large or small Daniel Povey 2022-07-10 10:13:55 +08:00
• 2f73434541 Reduce debug frequency Daniel Povey 2022-07-10 06:44:50 +08:00
• b3bb2dac6f Iterative, more principled way of estimating param_cov Daniel Povey 2022-07-10 06:28:01 +08:00
• d139c18f22 Max eig of Q limited to 5 times the mean Daniel Povey 2022-07-09 14:30:03 +08:00
• ffeef4ede4 Remove rank-1 dims, meaning where size==numel(), from processing. Daniel Povey 2022-07-09 13:36:48 +08:00
• 2fc9eb9789 Respect param_pow Daniel Povey 2022-07-09 12:49:04 +08:00
• 209acaf6e4 Increase lr_update_period to 200. The update takes about 2 minutes, fore entire model. Daniel Povey 2022-07-09 11:36:54 +08:00
• 61cab3ab65 introduce grad_cov_period Daniel Povey 2022-07-09 10:29:23 +08:00
• 35a51bc153 Reduce debug probs Daniel Povey 2022-07-09 10:22:19 +08:00
• 65bc964854 Fix bug for scalar update Daniel Povey 2022-07-09 10:14:20 +08:00
• aa2237a793 Bug fix Daniel Povey 2022-07-09 10:11:54 +08:00
• 50ee414486 Fix train.py for new optimizer Daniel Povey 2022-07-09 10:09:53 +08:00
• 6810849058 Implement new version of learning method. Does more complete diagonalization of grads than the previous methods. Daniel Povey 2022-07-09 10:02:17 +08:00
• a9edecd32c Conformed that symmetrizing helps because of interaction with regular update; still meta_lr_scale=0 best :-( Daniel Povey 2022-07-09 05:20:04 +08:00
• ad68987423 minor fix yaozengwei 2022-07-08 17:28:45 +08:00
• e3e8b1990c use i&i-1 to judge if it is a power of 2 yaozengwei 2022-07-08 17:16:10 +08:00
• 2057124004 fix bug, >> -> << yaozengwei 2022-07-08 16:45:12 +08:00
• 5cfdbd3699 replace torch.div() with << yaozengwei 2022-07-08 16:41:46 +08:00
• 1a663f4759
  Merge 5ea58a446514f0cd1786c66a5058f7d735a53806 into 6c69c4e2533a1dd8d2d06583e734ed77c7e56752 Zengwei Yao 2022-07-08 15:49:32 +08:00
• 6c69c4e253
  Support running icefall outside of a git tracked directory. (#470) Fangjun Kuang 2022-07-08 15:03:07 +08:00
• 73205de3ae Minor fixes. Fangjun Kuang 2022-07-08 15:02:36 +08:00
• 517febb006 Support running icefall outside of a git tracked directory. Fangjun Kuang 2022-07-08 14:58:31 +08:00
• aed2093c83 update multi_quantization installation Guo Liyong 2022-07-08 12:20:25 +08:00
• 52bfb2b018 This works better for reasons I dont understand. transpose is enough, same as symmetrizing. Daniel Povey 2022-07-08 11:53:59 +08:00
• dc40220951 change context size to 1 Yuekai Zhang 2022-07-08 03:13:09 +00:00
• e9ab1ddd39 Inconseqeuential config change Daniel Povey 2022-07-08 11:03:16 +08:00