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

• 407e8aeff7 Use a different seed for each epoch. Fangjun Kuang 2022-02-21 14:27:26 +08:00
• 9f69dafc92 Update results. Fangjun Kuang 2022-02-21 13:08:56 +08:00
• 791f54c8c2 Reset seed at the beginning of each epoch. Fangjun Kuang 2022-02-21 12:08:37 +08:00
• 711c1ccbcd
  Merge 136c03d040ad8d81ae8d0ccf5a3a5d9d11d9c79c into cbf8c18ebd274dfeea9b8aa224ff5faad713c28c Fangjun Kuang 2022-02-20 09:14:54 +08:00
• 4aead98812 Minor fixes. Fangjun Kuang 2022-02-19 23:09:12 +08:00
• 03a2a931d3 Add modified transducer for aishell. Fangjun Kuang 2022-02-19 22:37:32 +08:00
• cbf8c18ebd
  Minor fixes for aishell (#218) Fangjun Kuang 2022-02-19 22:28:19 +08:00
• 05de8e3b2e Minor fixes. Fangjun Kuang 2022-02-19 22:26:11 +08:00
• ecea4aac2f Minor fixes to aishell. Fangjun Kuang 2022-02-19 22:24:20 +08:00
• 277cc3f9bf
  update aishell-1 recipe with k2.rnnt_loss (#215) PF Luo 2022-02-19 15:56:39 +08:00
• 827b9df51a
  Updated Aishell-1 transducer-stateless result (#217) Duo Ma 2022-02-19 15:56:04 +08:00
• 5d68890c69
  Update RESULTS.md Duo Ma 2022-02-19 14:40:59 +08:00
• ed0f48b562
  Update RESULTS.md Duo Ma 2022-02-19 14:38:47 +08:00
• ff670ba714 add pretrained model link to result.md PingFeng Luo 2022-02-19 13:58:31 +08:00
• 753cd9033e
  Update README.md alexei-v-ivanov 2022-02-18 16:52:55 -08:00
• a4e89834d9 typo PingFeng Luo 2022-02-18 19:00:52 +08:00
• fb68c4f212 fix flak8 style PingFeng Luo 2022-02-18 18:51:39 +08:00
• 7a8875ebcb update aishell-1 recipe with k2.rnnt_loss PingFeng Luo 2022-02-18 18:26:19 +08:00
• 61b0019ffd Make the probability to select a batch from GigaSpeech configurable. Fangjun Kuang 2022-02-17 18:34:48 +08:00
• 981bf74364 Fix decode.py Fangjun Kuang 2022-02-17 18:31:50 +08:00
• b702281e90
  Use k2 pruned transducer loss to train conformer-transducer model (#194) Wei Kang 2022-02-17 13:33:54 +08:00
• a432e356a5 Minor fixes pkufool 2022-02-17 12:47:17 +08:00
• 1930d72b17 Display losses for gigaspeech and librispeech separately. Fangjun Kuang 2022-02-16 18:38:56 +08:00
• f8065fb279 update this pr Mingshuang Luo 2022-02-16 18:27:07 +08:00
• e8eb408760
  Incremental pruning threshold (#214) Wang, Guanbo 2022-02-16 03:59:27 -05:00
• ff88356ee4 minor fix wgb14 2022-02-16 02:38:58 -05:00
• 073c3bc97d black wgb14 2022-02-16 02:08:44 -05:00
• 059457f622 flake8 wgb14 2022-02-16 02:04:09 -05:00
• 55c0a7ddcd Incremental pruning threshold wgb14 2022-02-16 01:58:44 -05:00
• 018d03cd08 Finish training code. Fangjun Kuang 2022-02-16 14:24:34 +08:00
• e978948a26 Copy files. Fangjun Kuang 2022-02-16 12:43:26 +08:00
• d6fefe4e34 Minor fixes Fangjun Kuang 2022-02-16 12:41:47 +08:00
• 7cbd6d11ba Finish preparing training datasets. Fangjun Kuang 2022-02-16 12:27:48 +08:00
• fb1e2ffdc1 Begin to use multiple datasets. Fangjun Kuang 2022-02-15 20:24:48 +08:00
• adb54aea91 Add backoff arcs to the start state to handle OOV word. Fangjun Kuang 2022-02-15 12:33:53 +08:00
• 47e49a6663 change transcript_words.txt Mingshuang Luo 2022-02-15 12:33:51 +08:00
• b429efa661 Add decode.py Guanbo Wang 2022-02-14 16:31:04 -08:00
• c62e0b7f2c use 3gram to decode, 4gram to rescore Guanbo Wang 2022-02-14 16:30:09 -08:00
• 2af1b3af98 Remove ReLU in attention Daniel Povey 2022-02-14 19:39:19 +08:00
• d187ad8b73 Change max_frames from 0.2 to 0.15 Daniel Povey 2022-02-11 16:24:17 +08:00
• 5af23efa69 Keep disambig tokens and backoff arcs in LG. Fangjun Kuang 2022-02-10 20:28:59 +08:00
• ecfb28da20 Update asr_datamodule.py Mingshuang Luo 2022-02-10 16:08:22 +08:00
• 4cd2c02fff Fix num_time_masks code; revert 0.8 to 0.9 Daniel Povey 2022-02-10 15:53:11 +08:00
• c170c53006 Change p=0.9 to p=0.8 in SpecAug Daniel Povey 2022-02-10 14:59:14 +08:00
• efc8b7167a
  Merge c2c3e2ba76ecf231fb2b8bfabdc1da0dac4bd377 into 70a3c56a18d726d0a04c2774247e132e4464f54f PF Luo 2022-02-09 14:59:18 -05:00
• 8aa50df4f0 Change p=0.5->0.9, mask_fraction 0.3->0.2 Daniel Povey 2022-02-09 22:52:53 +08:00
• 70a3c56a18
  Fix librispeech train.py (#211) Wang, Guanbo 2022-02-09 03:42:28 -05:00
• 5802097652 remove note wgb14 2022-02-09 03:34:16 -05:00
• 159803fccb fix librispeech train.py wgb14 2022-02-09 03:29:50 -05:00
• 136c03d040 Fix decoding. Fangjun Kuang 2022-02-09 12:15:12 +08:00
• dd19a6a2b1 Fix to num_feature_masks bug I introduced; reduce max_frames_mask_fraction 0.4->0.3 Daniel Povey 2022-02-09 12:02:19 +08:00
• bd36216e8c Use much more aggressive SpecAug setup Daniel Povey 2022-02-08 21:55:20 +08:00
• 954b4efff3 WIP: Use shallow fusion in modified beam search. Fangjun Kuang 2022-02-08 20:40:45 +08:00
• beaf5bfbab Merge specaug change from Mingshuang. Daniel Povey 2022-02-08 19:42:23 +08:00
• 395065eb11 Merge branch 'spec-augment-change' of https://github.com/luomingshuang/icefall into attention_relu_specaug Daniel Povey 2022-02-08 19:40:33 +08:00
• e165bdf4af Update results for transducer_stateless after training for more epochs. Fangjun Kuang 2022-02-08 15:30:20 +08:00
• be1c86b06c
  print num_frame as %.2f (#204) Wang, Guanbo 2022-02-08 01:56:58 -05:00
• 9847e0f9d9 Merge remote-tracking branch 'upstream/master' into fix_num_frame Guanbo Wang 2022-02-08 01:46:02 -05:00
• 3912d12e6a print num_frame as %.2f wgb14 2022-02-08 01:35:38 -05:00
• 7472ef7d0e update asr_datamodule.py Mingshuang Luo 2022-02-08 14:35:33 +08:00
• 3323cabf46 Experiments based on SpecAugment change Mingshuang Luo 2022-02-08 14:25:31 +08:00
• 0baa7026f0
  Merge branch 'k2-fsa:master' into master Mingshuang Luo 2022-02-08 14:22:44 +08:00
• 09bbed3275 Use CTC loss as auxiliary loss. Fangjun Kuang 2022-02-07 19:10:21 +08:00
• f2a45eb38d Remove learnable offset, use relu instead. Fangjun Kuang 2022-02-07 19:02:47 +08:00
• b3ea50126a Merge remote-tracking branch 'dan/master' into frame-shift Fangjun Kuang 2022-02-07 18:56:36 +08:00
• 27fa5f05d3
  Update git SHA-1 in RESULTS.md for transducer_stateless. (#202) Fangjun Kuang 2022-02-07 18:45:45 +08:00
• 82f19baa8b Update git SHA-1 in RESULTS.md for transducer_stateless. Fangjun Kuang 2022-02-07 18:43:53 +08:00
• a8150021e0
  Use modified transducer loss in training. (#179) Fangjun Kuang 2022-02-07 18:37:36 +08:00
• 5835c5f307
  Merge 69679e023e147fe4d09d80a9e1b1b5c9b8b5f212 into 35ecd7e5629630242d28aa35004c8394ff7b1f91 Fangjun Kuang 2022-02-07 16:59:59 +08:00
• 4159d6fbf6 Merge remote-tracking branch 'dan/master' into rnnt-modified Fangjun Kuang 2022-02-07 16:43:14 +08:00
• 45866f95b4 Minor fixes. Fangjun Kuang 2022-02-07 16:39:39 +08:00
• e614e0bd45 Fix a typo. Fangjun Kuang 2022-02-07 16:32:28 +08:00
• 3b93761199 Update RESULTS. Fangjun Kuang 2022-02-07 16:31:10 +08:00
• a859dcb205 Remove learnable offset, use relu instead. Daniel Povey 2022-02-07 12:14:48 +08:00
• 8653b6a68a Apply random frame shift along the time axis. Fangjun Kuang 2022-02-07 12:09:26 +08:00
• bdf02f69d6 pad 1 without 0.01 weight for exp Mingshuang Luo 2022-02-07 11:07:57 +08:00
• 35ecd7e562
  Fix torch.nn.Embedding error for torch below 1.8.0 (#198) Wei Kang 2022-02-06 21:59:54 +08:00
• 48a764eccf Add min in q,k,v of attention Daniel Povey 2022-02-06 21:19:37 +08:00
• 8f8ec223a7 Changes to fbank computation, use lilcom chunky writer Daniel Povey 2022-02-06 21:18:40 +08:00
• fcd25bdfff Fix torch.nn.Embedding error for torch below 1.8.0 pkufool 2022-02-06 18:22:56 +08:00
• e6eb398d3f
  Merge 3c89734b79357508c0274b04895f64cc7d65a446 into 5ae80dfca7dab8f6faf99237effc17624f4e15de Fangjun Kuang 2022-01-31 18:18:04 -05:00
• e1936fa5a8 Fix typo. Fangjun Kuang 2022-01-29 23:44:06 +08:00
• 534cac4406 Minor fixes. Fangjun Kuang 2022-01-29 12:59:01 +08:00
• 77261bc575 Add modified beam search. Fangjun Kuang 2022-01-28 23:51:04 +08:00
• 3e3c1a6aee update docs pkufool 2022-01-28 20:05:48 +08:00
• 08729f88b1 Fix the mismatch of forward & backward joiner label pkufool 2022-01-28 18:21:15 +08:00
• c3b3123b27 Add modified beam search. Fangjun Kuang 2022-01-28 16:20:42 +08:00
• 5d4fd85715 Fix conflicts pkufool 2022-01-27 19:29:23 +08:00
• 29fd69d480 Merge branch 'master' into rnnt_aishell pkufool 2022-01-27 19:22:26 +08:00
• ff7af3586a Decrease the model size and other fixes pkufool 2022-01-27 19:18:47 +08:00
• 5ae80dfca7
  Minor fixes (#193) Wei Kang 2022-01-27 18:01:17 +08:00
• 18f997fe51 Fix bugs in backward decoder pkufool 2022-01-27 17:34:44 +08:00
• 3b6d416c4f Fix style pkufool 2022-01-27 17:11:36 +08:00
• 8f43ed10d6 Minor fixes pkufool 2022-01-27 17:03:49 +08:00
• 88ea4532c0 Using k2 pruned version transducer loss to train model pkufool 2022-01-27 16:36:47 +08:00
• 8b7f43a027 Add backward decoder pkufool 2022-01-26 14:27:41 +08:00
• 7df98eb000 pad 1 with torch.nn.functional.pad Mingshuang Luo 2022-01-26 13:00:18 +08:00
• cbc6f01861 modified conv1dabs attention with pad 1 Mingshuang Luo 2022-01-26 11:46:03 +08:00
• 4749619e5a Minor fixes after review. Fangjun Kuang 2022-01-25 18:46:35 +08:00
• dd2acd89fd Modified attention. Fangjun Kuang 2022-01-25 17:43:04 +08:00