feat: upgrade local speech recognition engine to SenseVoice-Small with hardware audio enhancements

kouyu_english/assets/models/sherpa/tokens.txt

@@ -1,502 +0,0 @@
-<blk> 0
-<sos/eos> 1
-<unk> 2
-S 3
-▁THE 4
-▁A 5
-T 6
-▁AND 7
-ED 8
-▁OF 9
-▁TO 10
-E 11
-D 12
-N 13
-ING 14
-▁IN 15
-Y 16
-M 17
-C 18
-▁I 19
-A 20
-P 21
-▁HE 22
-R 23
-O 24
-L 25
-RE 26
-I 27
-U 28
-ER 29
-▁IT 30
-LY 31
-▁THAT 32
-▁WAS 33
-▁ 34
-▁S 35
-AR 36
-▁BE 37
-F 38
-▁C 39
-IN 40
-B 41
-▁FOR 42
-OR 43
-LE 44
-' 45
-▁HIS 46
-▁YOU 47
-AL 48
-▁RE 49
-V 50
-▁B 51
-G 52
-RI 53
-▁E 54
-▁WITH 55
-▁T 56
-▁AS 57
-LL 58
-▁P 59
-▁HER 60
-ST 61
-▁HAD 62
-▁SO 63
-▁F 64
-W 65
-CE 66
-▁IS 67
-ND 68
-▁NOT 69
-TH 70
-▁BUT 71
-EN 72
-▁SHE 73
-▁ON 74
-VE 75
-ON 76
-SE 77
-▁DE 78
-UR 79
-▁G 80
-CH 81
-K 82
-TER 83
-▁AT 84
-IT 85
-▁ME 86
-RO 87
-NE 88
-RA 89
-ES 90
-IL 91
-NG 92
-IC 93
-▁NO 94
-▁HIM 95
-ENT 96
-IR 97
-▁WE 98
-H 99
-▁DO 100
-▁ALL 101
-▁HAVE 102
-LO 103
-▁BY 104
-▁MY 105
-▁MO 106
-▁THIS 107
-LA 108
-▁ST 109
-▁WHICH 110
-▁CON 111
-▁THEY 112
-CK 113
-TE 114
-▁SAID 115
-▁FROM 116
-▁GO 117
-▁WHO 118
-▁TH 119
-▁OR 120
-▁D 121
-▁W 122
-VER 123
-LI 124
-▁SE 125
-▁ONE 126
-▁CA 127
-▁AN 128
-▁LA 129
-▁WERE 130
-EL 131
-▁HA 132
-▁MAN 133
-▁FA 134
-▁EX 135
-AD 136
-▁SU 137
-RY 138
-▁MI 139
-AT 140
-▁BO 141
-▁WHEN 142
-AN 143
-THER 144
-PP 145
-ATION 146
-▁FI 147
-▁WOULD 148
-▁PRO 149
-OW 150
-ET 151
-▁O 152
-▁THERE 153
-▁HO 154
-ION 155
-▁WHAT 156
-▁FE 157
-▁PA 158
-US 159
-MENT 160
-▁MA 161
-UT 162
-▁OUT 163
-▁THEIR 164
-▁IF 165
-▁LI 166
-▁K 167
-▁WILL 168
-▁ARE 169
-ID 170
-▁RO 171
-DE 172
-TION 173
-▁WA 174
-PE 175
-▁UP 176
-▁SP 177
-▁PO 178
-IGHT 179
-▁UN 180
-RU 181
-▁LO 182
-AS 183
-OL 184
-▁LE 185
-▁BEEN 186
-▁SH 187
-▁RA 188
-▁SEE 189
-KE 190
-UL 191
-TED 192
-▁SA 193
-UN 194
-UND 195
-ANT 196
-▁NE 197
-IS 198
-▁THEM 199
-CI 200
-GE 201
-▁COULD 202
-▁DIS 203
-OM 204
-ISH 205
-HE 206
-EST 207
-▁SOME 208
-ENCE 209
-ITY 210
-IVE 211
-▁US 212
-▁MORE 213
-▁EN 214
-ARD 215
-ATE 216
-▁YOUR 217
-▁INTO 218
-▁KNOW 219
-▁CO 220
-ANCE 221
-▁TIME 222
-▁WI 223
-▁YE 224
-AGE 225
-▁NOW 226
-TI 227
-FF 228
-ABLE 229
-▁VERY 230
-▁LIKE 231
-AM 232
-HI 233
-Z 234
-▁OTHER 235
-▁THAN 236
-▁LITTLE 237
-▁DID 238
-▁LOOK 239
-TY 240
-ERS 241
-▁CAN 242
-▁CHA 243
-▁AR 244
-X 245
-FUL 246
-UGH 247
-▁BA 248
-▁DAY 249
-▁ABOUT 250
-TEN 251
-IM 252
-▁ANY 253
-▁PRE 254
-▁OVER 255
-IES 256
-NESS 257
-ME 258
-BLE 259
-▁M 260
-ROW 261
-▁HAS 262
-▁GREAT 263
-▁VI 264
-TA 265
-▁AFTER 266
-PER 267
-▁AGAIN 268
-HO 269
-SH 270
-▁UPON 271
-▁DI 272
-▁HAND 273
-▁COM 274
-IST 275
-TURE 276
-▁STA 277
-▁THEN 278
-▁SHOULD 279
-▁GA 280
-OUS 281
-OUR 282
-▁WELL 283
-▁ONLY 284
-MAN 285
-▁GOOD 286
-▁TWO 287
-▁MAR 288
-▁SAY 289
-▁HU 290
-TING 291
-▁OUR 292
-RESS 293
-▁DOWN 294
-IOUS 295
-▁BEFORE 296
-▁DA 297
-▁NA 298
-QUI 299
-▁MADE 300
-▁EVERY 301
-▁OLD 302
-▁EVEN 303
-IG 304
-▁COME 305
-▁GRA 306
-▁RI 307
-▁LONG 308
-OT 309
-SIDE 310
-WARD 311
-▁FO 312
-▁WHERE 313
-MO 314
-LESS 315
-▁SC 316
-▁MUST 317
-▁NEVER 318
-▁HOW 319
-▁CAME 320
-▁SUCH 321
-▁RU 322
-▁TAKE 323
-▁WO 324
-▁CAR 325
-UM 326
-AK 327
-▁THINK 328
-▁MUCH 329
-▁MISTER 330
-▁MAY 331
-▁JO 332
-▁WAY 333
-▁COMP 334
-▁THOUGHT 335
-▁STO 336
-▁MEN 337
-▁BACK 338
-▁DON 339
-J 340
-▁LET 341
-▁TRA 342
-▁FIRST 343
-▁JUST 344
-▁VA 345
-▁OWN 346
-▁PLA 347
-▁MAKE 348
-ATED 349
-▁HIMSELF 350
-▁WENT 351
-▁PI 352
-GG 353
-RING 354
-▁DU 355
-▁MIGHT 356
-▁PART 357
-▁GIVE 358
-▁IMP 359
-▁BU 360
-▁PER 361
-▁PLACE 362
-▁HOUSE 363
-▁THROUGH 364
-IAN 365
-▁SW 366
-▁UNDER 367
-QUE 368
-▁AWAY 369
-▁LOVE 370
-QUA 371
-▁LIFE 372
-▁GET 373
-▁WITHOUT 374
-▁PASS 375
-▁TURN 376
-IGN 377
-▁HEAD 378
-▁MOST 379
-▁THOSE 380
-▁SHALL 381
-▁EYES 382
-▁COL 383
-▁STILL 384
-▁NIGHT 385
-▁NOTHING 386
-ITION 387
-HA 388
-▁TELL 389
-▁WORK 390
-▁LAST 391
-▁NEW 392
-▁FACE 393
-▁HI 394
-▁WORD 395
-▁FOUND 396
-▁COUNT 397
-▁OB 398
-▁WHILE 399
-▁SHA 400
-▁MEAN 401
-▁SAW 402
-▁PEOPLE 403
-▁FRIEND 404
-▁THREE 405
-▁ROOM 406
-▁SAME 407
-▁THOUGH 408
-▁RIGHT 409
-▁CHILD 410
-▁FATHER 411
-▁ANOTHER 412
-▁HEART 413
-▁WANT 414
-▁TOOK 415
-OOK 416
-▁LIGHT 417
-▁MISSUS 418
-▁OPEN 419
-▁JU 420
-▁ASKED 421
-PORT 422
-▁LEFT 423
-▁JA 424
-▁WORLD 425
-▁HOME 426
-▁WHY 427
-▁ALWAYS 428
-▁ANSWER 429
-▁SEEMED 430
-▁SOMETHING 431
-▁GIRL 432
-▁BECAUSE 433
-▁NAME 434
-▁TOLD 435
-▁NI 436
-▁HIGH 437
-IZE 438
-▁WOMAN 439
-▁FOLLOW 440
-▁RETURN 441
-▁KNEW 442
-▁EACH 443
-▁KIND 444
-▁JE 445
-▁ACT 446
-▁LU 447
-▁CERTAIN 448
-▁YEARS 449
-▁QUITE 450
-▁APPEAR 451
-▁BETTER 452
-▁HALF 453
-▁PRESENT 454
-▁PRINCE 455
-SHIP 456
-▁ALSO 457
-▁BEGAN 458
-▁HAVING 459
-▁ENOUGH 460
-▁PERSON 461
-▁LADY 462
-▁WHITE 463
-▁COURSE 464
-▁VOICE 465
-▁SPEAK 466
-▁POWER 467
-▁MORNING 468
-▁BETWEEN 469
-▁AMONG 470
-▁KEEP 471
-▁WALK 472
-▁MATTER 473
-▁TEA 474
-▁BELIEVE 475
-▁SMALL 476
-▁TALK 477
-▁FELT 478
-▁HORSE 479
-▁MYSELF 480
-▁SIX 481
-▁HOWEVER 482
-▁FULL 483
-▁HERSELF 484
-▁POINT 485
-▁STOOD 486
-▁HUNDRED 487
-▁ALMOST 488
-▁SINCE 489
-▁LARGE 490
-▁LEAVE 491
-▁PERHAPS 492
-▁DARK 493
-▁SUDDEN 494
-▁REPLIED 495
-▁ANYTHING 496
-▁WONDER 497
-▁UNTIL 498
-Q 499
-#0 500
-#1 501

kouyu_english/lib/core/sherpa_stt_service.dart

@@ -15,7 +15,7 @@ class SherpaSttService {
 
   bool get isReady => _isInitialized && _recognizer != null;
 
-  /// Initializes Sherpa-ONNX bindings and unpacks bundled model assets to local disk if needed.
+  /// Initializes SenseVoice-Small ONNX bindings and unpacks bundled model assets to local disk if needed.
   Future<bool> initialize({String? nativeLibDir}) async {
     if (_isInitialized) return true;
     if (_isInitializing) return false;
@@ -29,32 +29,30 @@ class SherpaSttService {
       }
 
       final docDir = await getApplicationDocumentsDirectory();
-      final modelDir = Directory('${docDir.path}/sherpa_models');
+      final modelDir = Directory('${docDir.path}/sense_voice_models');
       if (!await modelDir.exists()) {
         await modelDir.create(recursive: true);
       }
 
       final modelFiles = [
-        'encoder-epoch-99-avg-1.int8.onnx',
+        'model.int8.onnx',
-        'decoder-epoch-99-avg-1.int8.onnx',
-        'joiner-epoch-99-avg-1.int8.onnx',
         'tokens.txt',
       ];
 
       for (final filename in modelFiles) {
         final targetFile = File('${modelDir.path}/$filename');
         if (!await targetFile.exists() || (await targetFile.length()) == 0) {
-          final ByteData data = await rootBundle.load('assets/models/sherpa/$filename');
+          final ByteData data = await rootBundle.load('assets/models/sense_voice/$filename');
           final Uint8List bytes = data.buffer.asUint8List(data.offsetInBytes, data.lengthInBytes);
           await targetFile.writeAsBytes(bytes, flush: true);
         }
       }
 
       final modelConfig = sherpa_onnx.OfflineModelConfig(
-        transducer: sherpa_onnx.OfflineTransducerModelConfig(
+        senseVoice: sherpa_onnx.OfflineSenseVoiceModelConfig(
-          encoder: '${modelDir.path}/encoder-epoch-99-avg-1.int8.onnx',
+          model: '${modelDir.path}/model.int8.onnx',
-          decoder: '${modelDir.path}/decoder-epoch-99-avg-1.int8.onnx',
+          language: 'auto',
-          joiner: '${modelDir.path}/joiner-epoch-99-avg-1.int8.onnx',
+          useInverseTextNormalization: true,
         ),
         tokens: '${modelDir.path}/tokens.txt',
         numThreads: 2,
@@ -69,17 +67,17 @@ class SherpaSttService {
       _recognizer = sherpa_onnx.OfflineRecognizer(recognizerConfig);
       _isInitialized = true;
       _isInitializing = false;
-      debugPrint('[SherpaSttService] Local ONNX ASR engine initialized successfully.');
+      debugPrint('[SherpaSttService] SenseVoice-Small ONNX ASR engine initialized successfully.');
       return true;
     } catch (e, stack) {
-      debugPrint('[SherpaSttService] Failed to initialize local ASR engine: $e\n$stack');
+      debugPrint('[SherpaSttService] Failed to initialize SenseVoice ASR engine: $e\n$stack');
       _isInitializing = false;
       _isInitialized = false;
       return false;
     }
   }
 
-  /// Transcribes a local 16kHz mono WAV audio file.
+  /// Transcribes a local 16kHz mono WAV audio file using SenseVoice-Small.
   Future<String?> transcribeWav(String wavPath) async {
     try {
       if (!_isInitialized) {
@@ -115,14 +113,19 @@ class SherpaSttService {
     }
   }
 
-  /// Cleans and formats raw recognized text into natural English casing.
+  /// Cleans and formats raw recognized SenseVoice text (strips emotion/event tags, normalizes casing).
   String _cleanText(String text) {
     if (text.isEmpty) return text;
-    // Lowercase first to normalize uppercase model output
+    // Strip SenseVoice special tags like <|zh|>, <|en|>, <|NEUTRAL|>, <|HAPPY|>, <|Speech|>, <|withitn|>, <|woitn|>, etc.
-    final lower = text.toLowerCase().trim();
+    var cleaned = text.replaceAll(RegExp(r'<\|[a-zA-Z0-9_\-\s]+\|>'), '').trim();
-    if (lower.isEmpty) return lower;
+    if (cleaned.isEmpty) return cleaned;
-    // Capitalize the first letter
+    // Normalize consecutive spaces
-    return lower[0].toUpperCase() + lower.substring(1);
+    cleaned = cleaned.replaceAll(RegExp(r'\s+'), ' ').trim();
+    // Capitalize first character if it's a letter
+    if (cleaned.isNotEmpty && cleaned[0].toLowerCase() != cleaned[0].toUpperCase()) {
+      cleaned = cleaned[0].toUpperCase() + cleaned.substring(1);
+    }
+    return cleaned;
   }
 
   void dispose() {

kouyu_english/lib/core/voice_service.dart

@@ -81,6 +81,9 @@ class VoiceService {
         encoder: AudioEncoder.wav,
         sampleRate: 16000,
         numChannels: 1,
+        noiseSuppress: true,
+        echoCancel: true,
+        autoGain: true,
       ),
       path: '${recordings.path}/practice_$timestamp.wav',
     );

kouyu_english/pubspec.yaml

@@ -33,4 +33,4 @@ flutter:
   uses-material-design: true
   assets:
     - assets/config/
-    - assets/models/sherpa/
+    - assets/models/sense_voice/

kouyu_english/test/sherpa_stt_test.dart

@@ -1,5 +1,4 @@
 import 'dart:io';
-import 'dart:typed_data';
 import 'package:flutter_test/flutter_test.dart';
 import 'package:kouyu_english/core/sherpa_stt_service.dart';
 import 'package:sherpa_onnx/sherpa_onnx.dart' as sherpa_onnx;
@@ -7,19 +6,19 @@ import 'package:sherpa_onnx/sherpa_onnx.dart' as sherpa_onnx;
 void main() {
   TestWidgetsFlutterBinding.ensureInitialized();
 
-  test('SherpaSttService transcribes WAV audio file accurately', () async {
+  test('SenseVoice-Small ONNX transcribes WAV audio file accurately', () async {
     const macosDir = '/Users/shen/.pub-cache/hosted/pub.dev/sherpa_onnx_macos-1.13.8/macos';
     
-    // Test direct Sherpa ASR initialization and decoding with bundled test audio
+    // Test direct Sherpa ASR initialization and decoding with SenseVoice
     sherpa_onnx.initBindings(macosDir);
 
     final modelConfig = sherpa_onnx.OfflineModelConfig(
-      transducer: const sherpa_onnx.OfflineTransducerModelConfig(
+      senseVoice: const sherpa_onnx.OfflineSenseVoiceModelConfig(
-        encoder: 'assets/models/sherpa/encoder-epoch-99-avg-1.int8.onnx',
+        model: 'assets/models/sense_voice/model.int8.onnx',
-        decoder: 'assets/models/sherpa/decoder-epoch-99-avg-1.int8.onnx',
+        language: 'auto',
-        joiner: 'assets/models/sherpa/joiner-epoch-99-avg-1.int8.onnx',
+        useInverseTextNormalization: true,
       ),
-      tokens: 'assets/models/sherpa/tokens.txt',
+      tokens: 'assets/models/sense_voice/tokens.txt',
       numThreads: 2,
       debug: false,
     );
@@ -40,8 +39,8 @@ void main() {
       stream.acceptWaveform(samples: wave.samples, sampleRate: wave.sampleRate);
       recognizer.decode(stream);
       final result = recognizer.getResult(stream);
-      print("Transcribed result: ${result.text}");
+      print("SenseVoice transcribed result: ${result.text}");
-      expect(result.text.contains("NIGHTFALL"), isTrue);
+      expect(result.text.toLowerCase().contains("nightfall"), isTrue);
       stream.free();
     }
     recognizer.free();