echogarden 2.1.1 → 2.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +18 -15
- package/data/lexicons/heteronyms.en.json +327 -122
- package/data/lexicons/words.en.json +260 -0
- package/data/schemas/options.json +20 -4
- package/dist/api/Recognition.d.ts +3 -1
- package/dist/api/Recognition.js +17 -0
- package/dist/api/Recognition.js.map +1 -1
- package/dist/api/Synthesis.d.ts +2 -2
- package/dist/api/Synthesis.js +3 -3
- package/dist/api/Synthesis.js.map +1 -1
- package/dist/codecs/FFMpegTranscoder.js +2 -0
- package/dist/codecs/FFMpegTranscoder.js.map +1 -1
- package/dist/nlp/EspeakPhonemizer.d.ts +2 -2
- package/dist/nlp/EspeakPhonemizer.js +36 -36
- package/dist/nlp/Lexicon.d.ts +2 -0
- package/dist/nlp/Lexicon.js +19 -19
- package/dist/nlp/Lexicon.js.map +1 -1
- package/dist/nlp/PhoneConversion.d.ts +1 -0
- package/dist/nlp/PhoneConversion.js +151 -222
- package/dist/nlp/PhoneConversion.js.map +1 -1
- package/dist/recognition/DeepgramSTT.d.ts +11 -0
- package/dist/recognition/DeepgramSTT.js +64 -0
- package/dist/recognition/DeepgramSTT.js.map +1 -0
- package/dist/recognition/GoogleCloudSTT.js.map +1 -1
- package/dist/synthesis/{ElevenlabsTTS.d.ts → ElevenLabsTTS.d.ts} +3 -3
- package/dist/synthesis/{ElevenlabsTTS.js → ElevenLabsTTS.js} +3 -3
- package/dist/synthesis/{ElevenlabsTTS.js.map → ElevenLabsTTS.js.map} +1 -1
- package/dist/synthesis/EspeakTTS.d.ts +1 -1
- package/dist/synthesis/EspeakTTS.js +9 -8
- package/dist/synthesis/EspeakTTS.js.map +1 -1
- package/dist/synthesis/KokoroTTS.js +14 -14
- package/dist/synthesis/VitsTTS.js +9 -9
- package/dist/utilities/Utilities.d.ts +1 -0
- package/dist/utilities/Utilities.js +5 -0
- package/dist/utilities/Utilities.js.map +1 -1
- package/dist/utilities/WasmMemoryManager.d.ts +1 -1
- package/docs/CLI.md +1 -1
- package/docs/CUDA.md +17 -0
- package/docs/Development.md +10 -2
- package/docs/Engines.md +2 -1
- package/docs/Options.md +19 -14
- package/docs/Tasklist.md +0 -1
- package/docs/Technical.md +18 -11
- package/package.json +6 -6
- package/src/api/Recognition.ts +29 -1
- package/src/api/Synthesis.ts +7 -7
- package/src/codecs/FFMpegTranscoder.ts +2 -0
- package/src/nlp/EspeakPhonemizer.ts +36 -36
- package/src/nlp/Lexicon.ts +24 -21
- package/src/nlp/PhoneConversion.ts +176 -225
- package/src/recognition/DeepgramSTT.ts +136 -0
- package/src/recognition/GoogleCloudSTT.ts +0 -1
- package/src/synthesis/{ElevenlabsTTS.ts → ElevenLabsTTS.ts} +4 -4
- package/src/synthesis/EspeakTTS.ts +9 -8
- package/src/synthesis/KokoroTTS.ts +15 -15
- package/src/synthesis/VitsTTS.ts +9 -9
- package/src/utilities/Utilities.ts +6 -0
|
@@ -3,7 +3,7 @@ export function ipaPhoneToKirshenbaum(ipaPhone) {
|
|
|
3
3
|
for (const char of ipaPhone) {
|
|
4
4
|
const convertedChar = ipaToKirshenbaum[char];
|
|
5
5
|
if (convertedChar == undefined) {
|
|
6
|
-
throw new Error(`
|
|
6
|
+
throw new Error(`Couldn't convert IPA character '${char}' (part of phone '${ipaPhone}' the Kirshenbaum notation`);
|
|
7
7
|
}
|
|
8
8
|
result += convertedChar || '_';
|
|
9
9
|
}
|
|
@@ -212,256 +212,185 @@ const ipaToTimit = {
|
|
|
212
212
|
'ŋ̍': ['eng'],
|
|
213
213
|
'ɾ': ['dx'],
|
|
214
214
|
};
|
|
215
|
-
|
|
216
|
-
|
|
217
|
-
|
|
218
|
-
'
|
|
219
|
-
'
|
|
220
|
-
'
|
|
221
|
-
'
|
|
222
|
-
'
|
|
223
|
-
'
|
|
224
|
-
|
|
225
|
-
'!': '!',
|
|
226
|
-
'\'': '\'',
|
|
227
|
-
'ʰ': '#',
|
|
228
|
-
'$': '$',
|
|
229
|
-
'%': '%',
|
|
230
|
-
//'æ': '&',
|
|
231
|
-
'æ': 'a',
|
|
232
|
-
'ˈ': '\'',
|
|
233
|
-
'(': '(',
|
|
234
|
-
')': ')',
|
|
235
|
-
'ɾ': '*',
|
|
236
|
-
'+': '+',
|
|
237
|
-
'ˌ': ',',
|
|
238
|
-
'-': '-',
|
|
239
|
-
'.': '.',
|
|
240
|
-
'/': '/',
|
|
241
|
-
'ɒ': '0',
|
|
242
|
-
'ɜ': '3',
|
|
243
|
-
'ɵ': '8',
|
|
244
|
-
'ː': ':',
|
|
245
|
-
'ʲ': ';',
|
|
246
|
-
'<': '<',
|
|
247
|
-
'=': '=',
|
|
248
|
-
'>': '>',
|
|
249
|
-
'ʔ': '?',
|
|
250
|
-
'ə': '@',
|
|
251
|
-
'ɑ': 'A',
|
|
252
|
-
'β': 'B',
|
|
253
|
-
'ç': 'C',
|
|
254
|
-
'ð': 'D',
|
|
255
|
-
'ɛ': 'E',
|
|
256
|
-
'F': 'F',
|
|
257
|
-
'ɢ': 'G',
|
|
258
|
-
'ħ': 'H',
|
|
215
|
+
export const ipaToKirshenbaum = {
|
|
216
|
+
//// Vowels
|
|
217
|
+
// Close
|
|
218
|
+
'i': 'i',
|
|
219
|
+
'y': 'y',
|
|
220
|
+
'ɨ': 'i"',
|
|
221
|
+
'ʉ': 'u"',
|
|
222
|
+
'ɯ': 'u-',
|
|
223
|
+
'u': 'u',
|
|
224
|
+
// Near-close
|
|
259
225
|
'ɪ': 'I',
|
|
260
|
-
'
|
|
261
|
-
'
|
|
262
|
-
'
|
|
263
|
-
'ɱ': 'M',
|
|
264
|
-
'ŋ': 'N',
|
|
265
|
-
'ɔ': 'O',
|
|
266
|
-
'Φ': 'P',
|
|
267
|
-
'ɣ': 'Q',
|
|
268
|
-
'ʀ': 'R',
|
|
269
|
-
'ʃ': 'S',
|
|
270
|
-
'θ': 'T',
|
|
226
|
+
'ɩ': 'I',
|
|
227
|
+
'ᵻ': 'I',
|
|
228
|
+
'ʏ': 'I.',
|
|
271
229
|
'ʊ': 'U',
|
|
272
|
-
'
|
|
273
|
-
|
|
274
|
-
'χ': 'X',
|
|
275
|
-
'ø': 'Y',
|
|
276
|
-
'ʒ': 'Z',
|
|
277
|
-
'̪': '[',
|
|
278
|
-
'\\': '\\',
|
|
279
|
-
']': ']',
|
|
280
|
-
'^': '^',
|
|
281
|
-
'_': '_',
|
|
282
|
-
'`': '`',
|
|
283
|
-
'a': 'a',
|
|
284
|
-
'b': 'b',
|
|
285
|
-
'c': 'c',
|
|
286
|
-
'd': 'd',
|
|
230
|
+
'ɷ': 'U',
|
|
231
|
+
// Close-mid
|
|
287
232
|
'e': 'e',
|
|
288
|
-
'
|
|
289
|
-
'
|
|
290
|
-
'
|
|
291
|
-
'
|
|
292
|
-
'
|
|
293
|
-
'
|
|
294
|
-
'l': 'l',
|
|
295
|
-
'm': 'm',
|
|
296
|
-
'n': 'n',
|
|
233
|
+
'ø': 'Y',
|
|
234
|
+
//'ɘ': '@<umd>', // Reference
|
|
235
|
+
'ɘ': '@', // Simplified
|
|
236
|
+
'ɵ': '@.',
|
|
237
|
+
//'ɵ': '8', // eSpeak
|
|
238
|
+
'ɤ': 'o-',
|
|
297
239
|
'o': 'o',
|
|
298
|
-
|
|
299
|
-
'
|
|
300
|
-
|
|
301
|
-
'
|
|
302
|
-
'
|
|
303
|
-
'
|
|
304
|
-
'
|
|
305
|
-
'
|
|
306
|
-
'
|
|
307
|
-
'
|
|
308
|
-
|
|
309
|
-
'
|
|
310
|
-
'
|
|
311
|
-
'}': '}',
|
|
312
|
-
'̃': '~',
|
|
313
|
-
'': '',
|
|
314
|
-
// Extensions
|
|
315
|
-
'ɚ': '3',
|
|
316
|
-
'ɹ': 'r',
|
|
240
|
+
// Mid:
|
|
241
|
+
'ə': '@',
|
|
242
|
+
// Open-mid:
|
|
243
|
+
'ɛ': 'E',
|
|
244
|
+
'œ': 'W',
|
|
245
|
+
//'ɜ': '3', // eSpeak
|
|
246
|
+
'ɜ': 'V"',
|
|
247
|
+
'ɞ': 'O"',
|
|
248
|
+
'ʌ': 'V',
|
|
249
|
+
'ɔ': 'O',
|
|
250
|
+
// Near-open
|
|
251
|
+
//'æ': '&', // Reference. note: passing '&' to eSpeak in SSML (XML) mode will cause an error due to escaping conflict
|
|
252
|
+
'æ': 'a', // eSpeak
|
|
317
253
|
'ɐ': 'a#',
|
|
318
|
-
|
|
319
|
-
'
|
|
320
|
-
|
|
321
|
-
|
|
322
|
-
|
|
323
|
-
|
|
324
|
-
|
|
325
|
-
|
|
254
|
+
// Open
|
|
255
|
+
'a': 'a',
|
|
256
|
+
//'ɶ': '&.', // Reference. note: passing '&' to eSpeak in SSML (XML) mode will cause an error due to escaping conflict
|
|
257
|
+
'ɶ': 'W#', // eSpeak
|
|
258
|
+
'ä': 'a"',
|
|
259
|
+
'ɒ̈': 'A".',
|
|
260
|
+
'ɑ': 'A',
|
|
261
|
+
//'ɒ': 'A.', // Reference
|
|
262
|
+
'ɒ': '0', // eSpeak
|
|
263
|
+
// Rhotic
|
|
264
|
+
'ɚ': 'R',
|
|
265
|
+
//'ɚ': '3', // eSpeak
|
|
266
|
+
//'ɝ': 'R<umd>', // Reference
|
|
267
|
+
'ɝ': 'R', // Simplified
|
|
268
|
+
// More vowels
|
|
269
|
+
'ᵊ': '',
|
|
270
|
+
//// Consonants
|
|
271
|
+
// Nasals
|
|
326
272
|
'm': 'm',
|
|
273
|
+
'ɱ': 'M',
|
|
274
|
+
'n̪': 'n[',
|
|
275
|
+
'n': 'n',
|
|
276
|
+
'ɳ': 'n.',
|
|
277
|
+
'ṇ': 'n.',
|
|
278
|
+
'ɲ': 'n^',
|
|
279
|
+
'ŋ': 'N',
|
|
280
|
+
'ɴ': 'n"',
|
|
281
|
+
//'n͡g': 'n<lbv>',
|
|
282
|
+
// Stops
|
|
327
283
|
'p': 'p',
|
|
328
284
|
'b': 'b',
|
|
285
|
+
't̪': 't[',
|
|
286
|
+
'd̪': 'd[',
|
|
287
|
+
't': 't',
|
|
288
|
+
'd': 'd',
|
|
289
|
+
'ʈ': 't.',
|
|
290
|
+
'ṭ': 't.',
|
|
291
|
+
'ɖ': 'd.',
|
|
292
|
+
'ḍ': 'd.',
|
|
293
|
+
'c': 'c',
|
|
294
|
+
'ɟ': 'J',
|
|
295
|
+
'k': 'k',
|
|
296
|
+
'ɡ': 'g',
|
|
297
|
+
'q': 'q',
|
|
298
|
+
'ɢ': 'G',
|
|
299
|
+
//'k͡p': 't<lbv>',
|
|
300
|
+
//'ɡ͡b': 'd<lbv>',
|
|
301
|
+
'ʔ': '?',
|
|
302
|
+
// Fricatives
|
|
303
|
+
'φ': 'P',
|
|
329
304
|
'Φ': 'P',
|
|
330
305
|
'β': 'B',
|
|
331
|
-
'ʙ': 'b<trl>',
|
|
332
|
-
'pʼ': 'p`',
|
|
333
|
-
'ɓ': 'b`',
|
|
334
|
-
'ʘ': 'p!',
|
|
335
|
-
'ɱ': 'M',
|
|
336
306
|
'f': 'f',
|
|
337
307
|
'v': 'v',
|
|
338
|
-
'ʋ': 'r<lbd>',
|
|
339
|
-
'n\u032a': 'n[',
|
|
340
|
-
't\u032a': 't[',
|
|
341
308
|
'θ': 'T',
|
|
342
309
|
'ð': 'D',
|
|
343
|
-
'r\u032a': 'r[',
|
|
344
|
-
'l\u032a': 'l[',
|
|
345
|
-
't\u032a\u02bc': 't[`',
|
|
346
|
-
'ɗ': 'd`',
|
|
347
|
-
'ʇ': 't!',
|
|
348
|
-
'n': 'n',
|
|
349
|
-
't': 't',
|
|
350
|
-
'd': 'd',
|
|
351
310
|
's': 's',
|
|
352
311
|
'z': 'z',
|
|
353
|
-
'ɬ': 's<lat>',
|
|
354
|
-
'ɮ': 'z<lat>',
|
|
355
|
-
'ɹ': 'r',
|
|
356
|
-
'l': 'l',
|
|
357
|
-
'ʀ': 'r<trl>',
|
|
358
|
-
'ɾ': '*',
|
|
359
|
-
'ɺ': '*<lat>',
|
|
360
|
-
't\u02bc': 't`',
|
|
361
|
-
'ʗ': 'c!',
|
|
362
|
-
'ʖ': 'l!',
|
|
363
|
-
'ɳ': 'n.',
|
|
364
|
-
'ʈ': 't.',
|
|
365
|
-
'ɖ': 'd.',
|
|
366
312
|
'ʂ': 's.',
|
|
313
|
+
'ṣ': 's.',
|
|
367
314
|
'ʐ': 'z.',
|
|
368
|
-
|
|
369
|
-
'ɭ': 'l.',
|
|
370
|
-
'ɽ': '*.',
|
|
315
|
+
'ẓ': 'z.',
|
|
371
316
|
'ʃ': 'S',
|
|
372
317
|
'ʒ': 'Z',
|
|
373
|
-
'n^': 'n^',
|
|
374
|
-
'c': 'c',
|
|
375
|
-
'ɟ': 'J',
|
|
376
318
|
'ç': 'C',
|
|
377
319
|
'ʝ': 'C<vcd>',
|
|
378
|
-
'j': 'j',
|
|
379
|
-
'ɥ': 'j<rnd>',
|
|
380
|
-
'ʎ': 'l^',
|
|
381
|
-
'ʄ': 'J`',
|
|
382
|
-
'ŋ': 'N',
|
|
383
|
-
'k': 'k',
|
|
384
|
-
'g': 'g',
|
|
385
320
|
'x': 'x',
|
|
386
321
|
'ɣ': 'Q',
|
|
387
|
-
'
|
|
388
|
-
'
|
|
389
|
-
//'
|
|
390
|
-
'k\u02bc': 'k`',
|
|
391
|
-
'g\u02bc': 'g`',
|
|
392
|
-
'ʞ': 'k!',
|
|
393
|
-
'n\u2030g': 'n<lbv>',
|
|
394
|
-
'k\u2030p': 't<lbv>',
|
|
395
|
-
'g\u2030b': 'n<lbv>',
|
|
322
|
+
'χ': 'X',
|
|
323
|
+
'ʁ': 'g"', // Reference
|
|
324
|
+
//'ʁ': 'r', // eSpeak
|
|
396
325
|
'ʍ': 'w<vls>',
|
|
397
326
|
'w': 'w',
|
|
398
|
-
'ɴ': 'n'',
|
|
399
|
-
'q': 'q',
|
|
400
|
-
'ɢ': 'G',
|
|
401
|
-
'χ': 'X',
|
|
402
|
-
'ʁ': 'g'',
|
|
403
|
-
//'ʀ': 'r'',
|
|
404
|
-
'ʠ': 'q`',
|
|
405
|
-
'ʛ': 'G`',
|
|
406
327
|
'ħ': 'H',
|
|
407
328
|
'ʕ': 'H<vcd>',
|
|
408
|
-
'ʔ': '?',
|
|
409
329
|
'h': 'h',
|
|
410
330
|
'ɦ': 'h<?>',
|
|
411
|
-
|
|
412
|
-
'
|
|
413
|
-
'
|
|
414
|
-
'
|
|
415
|
-
'
|
|
416
|
-
'
|
|
417
|
-
'
|
|
418
|
-
'
|
|
419
|
-
'
|
|
420
|
-
|
|
421
|
-
'
|
|
422
|
-
'
|
|
423
|
-
'
|
|
424
|
-
'
|
|
425
|
-
'
|
|
426
|
-
'
|
|
427
|
-
|
|
428
|
-
|
|
429
|
-
'
|
|
430
|
-
'
|
|
431
|
-
'
|
|
432
|
-
|
|
433
|
-
'
|
|
434
|
-
'
|
|
435
|
-
'
|
|
436
|
-
|
|
437
|
-
'
|
|
438
|
-
'
|
|
439
|
-
'
|
|
440
|
-
'
|
|
441
|
-
|
|
442
|
-
'
|
|
443
|
-
|
|
444
|
-
'
|
|
445
|
-
'
|
|
446
|
-
'
|
|
447
|
-
''
|
|
448
|
-
'
|
|
449
|
-
|
|
450
|
-
'
|
|
451
|
-
'
|
|
452
|
-
'
|
|
453
|
-
|
|
454
|
-
'
|
|
455
|
-
'
|
|
456
|
-
'
|
|
457
|
-
|
|
458
|
-
'
|
|
459
|
-
//
|
|
460
|
-
|
|
461
|
-
'
|
|
331
|
+
// Approximants
|
|
332
|
+
'ʋ': 'r<lbd>',
|
|
333
|
+
'ɹ̪': 'r[',
|
|
334
|
+
'ɹ': 'r',
|
|
335
|
+
'ɻ': 'r.',
|
|
336
|
+
'ɻ̣': 'r.',
|
|
337
|
+
'j': 'j',
|
|
338
|
+
'ɥ': 'j<rnd>',
|
|
339
|
+
'ɰ': 'j<vel>',
|
|
340
|
+
// Laterals
|
|
341
|
+
'l̪': 'l[',
|
|
342
|
+
'l': 'l',
|
|
343
|
+
'ɭ': 'l.',
|
|
344
|
+
'ḷ': 'l.',
|
|
345
|
+
'ʎ': 'l^',
|
|
346
|
+
'ʟ': 'L',
|
|
347
|
+
// Trills
|
|
348
|
+
'ʙ': 'b<trl>',
|
|
349
|
+
//'r': 'r<trl>', // Reference alv trl
|
|
350
|
+
'r': 'R', // eSpeak
|
|
351
|
+
'ʀ': 'r"', // Reference uvl trl
|
|
352
|
+
// Flaps
|
|
353
|
+
'ɾ': '*',
|
|
354
|
+
'ɽ': '*.',
|
|
355
|
+
'ṛ': '*.',
|
|
356
|
+
// Ejectives
|
|
357
|
+
'pʼ': 'p`',
|
|
358
|
+
'tʼ': 't`',
|
|
359
|
+
'cʼ': 'c`',
|
|
360
|
+
'kʼ': 'k`',
|
|
361
|
+
'qʼ': 'q`',
|
|
362
|
+
'ʠ': 'q`',
|
|
363
|
+
// Implosives
|
|
364
|
+
'ɓ': 'b`',
|
|
365
|
+
'ɗ': 'd`',
|
|
366
|
+
'ʄ': 'J`',
|
|
367
|
+
'ɠ': 'g`',
|
|
368
|
+
'ʛ': 'G`',
|
|
369
|
+
// Clicks
|
|
370
|
+
'ʘ': 'p!',
|
|
371
|
+
'ǀ': 't!',
|
|
372
|
+
'ʇ': 't!',
|
|
373
|
+
'ǃ': 'c!',
|
|
374
|
+
'ǂ': 'c!',
|
|
375
|
+
'ʗ': 'c!',
|
|
376
|
+
'ʞ': 'k!',
|
|
377
|
+
'ǁ': 'l!',
|
|
378
|
+
'ʖ': 'l!',
|
|
379
|
+
// Lateral fricative
|
|
380
|
+
'ɬ': 'L',
|
|
381
|
+
'ɮ': 'z<lat>',
|
|
382
|
+
'ɫ': 'L',
|
|
383
|
+
// Lateral flap
|
|
384
|
+
'ɺ': '*<lat>',
|
|
385
|
+
// Other consonants
|
|
386
|
+
'ʰ': '#',
|
|
387
|
+
'ʲ': ';',
|
|
388
|
+
'̪': '[',
|
|
389
|
+
'̃': '~',
|
|
390
|
+
// Stress marks and other misc characters
|
|
391
|
+
'ˈ': '\'',
|
|
462
392
|
'ˌ': ',',
|
|
463
|
-
'
|
|
464
|
-
'
|
|
465
|
-
}
|
|
466
|
-
*/
|
|
393
|
+
'ː': ':',
|
|
394
|
+
'-': '-',
|
|
395
|
+
};
|
|
467
396
|
//# sourceMappingURL=PhoneConversion.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"PhoneConversion.js","sourceRoot":"","sources":["../../src/nlp/PhoneConversion.ts"],"names":[],"mappings":"AAAA,MAAM,UAAU,qBAAqB,CAAC,QAAgB;IACrD,IAAI,MAAM,GAAG,EAAE,CAAA;IAEf,KAAK,MAAM,IAAI,IAAI,QAAQ,EAAE,CAAC;QAC7B,MAAM,aAAa,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAA;QAE5C,IAAI,aAAa,IAAI,SAAS,EAAE,CAAC;YAChC,MAAM,IAAI,KAAK,CAAC,
|
|
1
|
+
{"version":3,"file":"PhoneConversion.js","sourceRoot":"","sources":["../../src/nlp/PhoneConversion.ts"],"names":[],"mappings":"AAAA,MAAM,UAAU,qBAAqB,CAAC,QAAgB;IACrD,IAAI,MAAM,GAAG,EAAE,CAAA;IAEf,KAAK,MAAM,IAAI,IAAI,QAAQ,EAAE,CAAC;QAC7B,MAAM,aAAa,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAA;QAE5C,IAAI,aAAa,IAAI,SAAS,EAAE,CAAC;YAChC,MAAM,IAAI,KAAK,CAAC,mCAAmC,IAAI,qBAAqB,QAAQ,4BAA4B,CAAC,CAAA;QAClH,CAAC;QAED,MAAM,IAAI,aAAa,IAAI,GAAG,CAAA;IAC/B,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED,MAAM,UAAU,oBAAoB,CAAC,OAAe,EAAE,aAAa,GAAG,CAAC;IACtE,IAAI,MAAM,GAAa,EAAE,CAAA;IAEzB,KAAK,MAAM,QAAQ,IAAI,OAAO,EAAE,CAAC;QAChC,MAAM,sBAAsB,GAAG,eAAe,CAAC,QAAQ,EAAE,aAAa,CAAC,CAAA;QAEvE,IAAI,sBAAsB,IAAI,SAAS,EAAE,CAAC;YACzC,MAAM,IAAI,KAAK,CAAC,oDAAoD,QAAQ,GAAG,CAAC,CAAA;QACjF,CAAC;QAED,MAAM,GAAG,CAAC,GAAG,MAAM,EAAE,GAAG,sBAAsB,CAAC,CAAA;IAChD,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED,MAAM,UAAU,eAAe,CAAC,QAAgB,EAAE,aAAa,GAAG,CAAC;IAClE,IAAI,MAAM,GAAG,UAAU,CAAC,QAAQ,CAAC,CAAA;IAEjC,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,OAAO,SAAS,CAAA;IACjB,CAAC;IAED,IAAI,aAAa,GAAG,CAAC,EAAE,CAAC;QACvB,MAAM,GAAG,sBAAsB,CAAC,MAAM,EAAE,aAAa,CAAC,CAAA;IACvD,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED,MAAM,UAAU,iBAAiB,CAAC,YAAoB;IACrD,OAAO,YAAY,CAAC,YAAY,CAAC,WAAW,EAAE,CAAC,CAAA;AAChD,CAAC;AAED,MAAM,UAAU,eAAe,CAAC,YAAoB;IACnD,OAAO,UAAU,CAAC,YAAY,CAAC,WAAW,EAAE,CAAC,CAAA;AAC9C,CAAC;AAED,MAAM,UAAU,sBAAsB,CAAC,MAAgB,EAAE,aAAa,GAAG,CAAC;IACzE,MAAM,MAAM,GAAa,EAAE,CAAA;IAE3B,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC5B,IAAI,KAAK,IAAI,OAAO,EAAE,CAAC;YACtB,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YAElB,SAAQ;QACT,CAAC;QAED,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,aAAa,EAAE,CAAC,EAAE,EAAE,CAAC;YACzC,MAAM,CAAC,IAAI,CAAC,GAAG,KAAK,IAAI,CAAC,EAAE,CAAC,CAAA;QAC7B,CAAC;IACF,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED,oCAAoC;AACpC,oEAAoE;AACpE,kEAAkE;AAClE,+DAA+D;AAC/D,sEAAsE;AACtE,MAAM,YAAY,GAAwC;IACzD,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,GAAG;IACT,KAAK,EAAE,GAAG;IACV,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,GAAG;IACT,KAAK,EAAE,GAAG;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,GAAG;IACT,KAAK,EAAE,GAAG;IACV,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,GAAG;IACT,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,KAAK;IACX,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,GAAG;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,GAAG;IACT,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,GAAG;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,GAAG;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,GAAG;CACT,CAAA;AAED,MAAM,UAAU,GAAwC;IACvD,GAAG,YAAY;IAEf,IAAI,EAAE,GAAG;IACT,MAAM,EAAE,IAAI;IACZ,KAAK,EAAE,GAAG;IACV,GAAG,EAAE,EAAE;IACP,KAAK,EAAE,GAAG;IACV,GAAG,EAAE,EAAE;IACP,KAAK,EAAE,GAAG;IACV,IAAI,EAAE,GAAG;IACT,KAAK,EAAE,IAAI;IACX,KAAK,EAAE,EAAE;IACT,GAAG,EAAE,EAAE;IACP,KAAK,EAAE,GAAG;IACV,IAAI,EAAE,GAAG;IACT,KAAK,EAAE,EAAE;IACT,IAAI,EAAE,GAAG;IACT,KAAK,EAAE,GAAG;IACV,GAAG,EAAE,EAAE;IACP,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,EAAE;IACP,KAAK,EAAE,EAAE;IACT,KAAK,EAAE,GAAG;IACV,GAAG,EAAE,EAAE;IACP,KAAK,EAAE,GAAG;IACV,IAAI,EAAE,GAAG;CACT,CAAA;AAED,MAAM,UAAU,GAA0C;IACzD,SAAS;IACT,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,KAAK,EAAE,CAAC,IAAI,EAAE,GAAG,CAAC,EAAE,IAAI;IACxB,GAAG,EAAE,CAAC,IAAI,CAAC,EAAE,eAAe;IAE5B,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,KAAK,EAAE,CAAC,IAAI,EAAE,GAAG,CAAC,EAAE,IAAI;IACxB,KAAK,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI;IAEzB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI;IAExB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,GAAG,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAEjB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,MAAM,CAAC;IACd,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,eAAe;IACnC,GAAG,EAAE,CAAC,KAAK,CAAC;IACZ,GAAG,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAEjB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,KAAK,EAAE,CAAC,IAAI,EAAE,GAAG,CAAC,EAAE,IAAI;IACxB,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,GAAG,EAAE,CAAC,IAAI,CAAC,EAAE,eAAe;IAE5B,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAClB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAElB,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,eAAe;IACnC,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,eAAe;IAE7B,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,EAAE,GAAG,CAAC,EAAE,IAAI;IAEvB,GAAG,EAAE,CAAC,IAAI,CAAC;IAEX,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAClB,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,IAAI;IAExB,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAClB,KAAK,EAAE,CAAC,IAAI,EAAE,GAAG,CAAC,EAAE,IAAI;IAExB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,EAAE,GAAG,CAAC,EAAE,IAAI;IACvB,IAAI,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,eAAe;IAEnC,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAElB,aAAa;IACb,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;IACjB,IAAI,EAAE,CAAC,KAAK,EAAE,IAAI,CAAC;IACnB,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;IACjB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,IAAI,EAAE,CAAC,IAAI,CAAC,EAAE,IAAI;IAClB,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;IACjB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,KAAK,EAAE,IAAI,CAAC;IACnB,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;IACjB,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;IACjB,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;IACjB,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,GAAG,CAAC;IACV,GAAG,EAAE,CAAC,IAAI,CAAC;IAEX,IAAI,EAAE,CAAC,IAAI,CAAC;IACZ,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,GAAG,EAAE,CAAC,IAAI,CAAC;IACX,IAAI,EAAE,CAAC,KAAK,CAAC;IACb,GAAG,EAAE,CAAC,IAAI,CAAC;CACX,CAAA;AAED,MAAM,CAAC,MAAM,gBAAgB,GAA2B;IACvD,WAAW;IAEX,QAAQ;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,GAAG;IAER,aAAa;IACb,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IAER,YAAY;IACZ,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,6BAA6B;IAC7B,GAAG,EAAE,GAAG,EAAE,aAAa;IACvB,GAAG,EAAE,IAAI;IACT,qBAAqB;IACrB,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,GAAG;IAER,OAAO;IACP,GAAG,EAAE,GAAG;IAER,YAAY;IACZ,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,qBAAqB;IACrB,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IAER,YAAY;IACZ,qHAAqH;IACrH,GAAG,EAAE,GAAG,EAAE,SAAS;IACnB,GAAG,EAAE,IAAI;IAET,OAAO;IACP,GAAG,EAAE,GAAG;IACR,sHAAsH;IACtH,GAAG,EAAE,IAAI,EAAE,SAAS;IACpB,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,KAAK;IACX,GAAG,EAAE,GAAG;IACR,yBAAyB;IACzB,GAAG,EAAE,GAAG,EAAE,SAAS;IAEnB,SAAS;IACT,GAAG,EAAE,GAAG;IACR,qBAAqB;IACrB,6BAA6B;IAC7B,GAAG,EAAE,GAAG,EAAE,aAAa;IAEvB,cAAc;IACd,GAAG,EAAE,EAAE;IAEP,eAAe;IAEf,SAAS;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,kBAAkB;IAElB,QAAQ;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,kBAAkB;IAClB,kBAAkB;IAClB,GAAG,EAAE,GAAG;IAER,aAAa;IACb,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,QAAQ;IACb,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI,EAAE,YAAY;IACvB,qBAAqB;IACrB,GAAG,EAAE,QAAQ;IACb,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,QAAQ;IACb,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,MAAM;IAEX,eAAe;IACf,GAAG,EAAE,QAAQ;IACb,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,QAAQ;IACb,GAAG,EAAE,QAAQ;IAEb,WAAW;IACX,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,GAAG;IAER,SAAS;IACT,GAAG,EAAE,QAAQ;IACb,qCAAqC;IACrC,GAAG,EAAE,GAAG,EAAE,SAAS;IACnB,GAAG,EAAE,IAAI,EAAE,oBAAoB;IAE/B,QAAQ;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,IAAI;IACT,IAAI,EAAE,IAAI;IAEV,YAAY;IACZ,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,GAAG,EAAE,IAAI;IAET,aAAa;IACb,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IAET,SAAS;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,IAAI;IAET,oBAAoB;IACpB,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,QAAQ;IACb,GAAG,EAAE,GAAG;IAER,eAAe;IACf,GAAG,EAAE,QAAQ;IAEb,mBAAmB;IACnB,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IAER,yCAAyC;IACzC,GAAG,EAAE,IAAI;IACT,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;IACR,GAAG,EAAE,GAAG;CACR,CAAA"}
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
import { RawAudio } from '../audio/AudioUtilities.js';
|
|
2
|
+
import { Timeline } from '../utilities/Timeline.js';
|
|
3
|
+
export declare function recognize(rawAudio: RawAudio, languageCode: string | undefined, options: DeepgramSTTOptions): Promise<{
|
|
4
|
+
transcript: string;
|
|
5
|
+
timeline: Timeline;
|
|
6
|
+
}>;
|
|
7
|
+
export interface DeepgramSTTOptions {
|
|
8
|
+
apiKey?: string;
|
|
9
|
+
model?: string;
|
|
10
|
+
}
|
|
11
|
+
export declare const defaultDeepgramSTTOptions: DeepgramSTTOptions;
|
|
@@ -0,0 +1,64 @@
|
|
|
1
|
+
import { request } from 'gaxios';
|
|
2
|
+
import { Logger } from '../utilities/Logger.js';
|
|
3
|
+
import { extendDeep } from '../utilities/ObjectUtilities.js';
|
|
4
|
+
import * as FFMpegTranscoder from '../codecs/FFMpegTranscoder.js';
|
|
5
|
+
export async function recognize(rawAudio, languageCode, options) {
|
|
6
|
+
const logger = new Logger();
|
|
7
|
+
logger.start('Initialize Deepgram recognition');
|
|
8
|
+
options = extendDeep(defaultDeepgramSTTOptions, options);
|
|
9
|
+
if (!options.apiKey) {
|
|
10
|
+
throw new Error('No Deepgram API key provided');
|
|
11
|
+
}
|
|
12
|
+
// Prepare API request
|
|
13
|
+
const params = {
|
|
14
|
+
model: options.model || 'whisper-large',
|
|
15
|
+
encoding: 'flac',
|
|
16
|
+
//punctuate: 'true', // Problem when enabled: words in timeline are not capitalized, causing errors
|
|
17
|
+
};
|
|
18
|
+
// Set language or enable auto-detection
|
|
19
|
+
if (languageCode) {
|
|
20
|
+
params.language = languageCode;
|
|
21
|
+
}
|
|
22
|
+
else {
|
|
23
|
+
params.detect_language = 'true';
|
|
24
|
+
}
|
|
25
|
+
// Set audio encoding parameters
|
|
26
|
+
logger.start('Convert audio to FLAC format');
|
|
27
|
+
const audioData = await FFMpegTranscoder.encodeFromChannels(rawAudio, FFMpegTranscoder.getDefaultFFMpegOptionsForSpeech('flac'));
|
|
28
|
+
logger.start('Send request to Deepgram API');
|
|
29
|
+
const response = await request({
|
|
30
|
+
method: 'POST',
|
|
31
|
+
url: 'https://api.deepgram.com/v1/listen',
|
|
32
|
+
params,
|
|
33
|
+
headers: {
|
|
34
|
+
'Authorization': `Token ${options.apiKey}`,
|
|
35
|
+
'Content-Type': 'audio/flac',
|
|
36
|
+
'Accept': 'application/json'
|
|
37
|
+
},
|
|
38
|
+
body: audioData,
|
|
39
|
+
responseType: 'json',
|
|
40
|
+
});
|
|
41
|
+
const deepgramResponse = response.data;
|
|
42
|
+
const firstAlternative = deepgramResponse.results?.channels[0]?.alternatives[0];
|
|
43
|
+
// Extract transcript and create timeline
|
|
44
|
+
const transcript = firstAlternative?.transcript || '';
|
|
45
|
+
let timeline = [];
|
|
46
|
+
// Extract word-level timing information if available
|
|
47
|
+
const words = firstAlternative?.words || [];
|
|
48
|
+
if (words.length > 0) {
|
|
49
|
+
timeline = words.map((word) => ({
|
|
50
|
+
type: 'word',
|
|
51
|
+
text: word.word,
|
|
52
|
+
startTime: word.start,
|
|
53
|
+
endTime: word.end,
|
|
54
|
+
confidence: word.confidence,
|
|
55
|
+
}));
|
|
56
|
+
}
|
|
57
|
+
logger.end();
|
|
58
|
+
return { transcript, timeline };
|
|
59
|
+
}
|
|
60
|
+
export const defaultDeepgramSTTOptions = {
|
|
61
|
+
apiKey: undefined,
|
|
62
|
+
model: 'nova-2'
|
|
63
|
+
};
|
|
64
|
+
//# sourceMappingURL=DeepgramSTT.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"DeepgramSTT.js","sourceRoot":"","sources":["../../src/recognition/DeepgramSTT.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,MAAM,QAAQ,CAAA;AAEhC,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAC/C,OAAO,EAAE,UAAU,EAAE,MAAM,iCAAiC,CAAA;AAE5D,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AAEjE,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,YAAgC,EAAE,OAA2B;IAChH,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAE3B,MAAM,CAAC,KAAK,CAAC,iCAAiC,CAAC,CAAA;IAE/C,OAAO,GAAG,UAAU,CAAC,yBAAyB,EAAE,OAAO,CAAC,CAAA;IAExD,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC;QACrB,MAAM,IAAI,KAAK,CAAC,8BAA8B,CAAC,CAAA;IAChD,CAAC;IAED,sBAAsB;IACtB,MAAM,MAAM,GAA2B;QACtC,KAAK,EAAE,OAAO,CAAC,KAAK,IAAI,eAAe;QACvC,QAAQ,EAAE,MAAM;QAChB,mGAAmG;KACnG,CAAA;IAED,wCAAwC;IACxC,IAAI,YAAY,EAAE,CAAC;QAClB,MAAM,CAAC,QAAQ,GAAG,YAAY,CAAA;IAC/B,CAAC;SAAM,CAAC;QACP,MAAM,CAAC,eAAe,GAAG,MAAM,CAAA;IAChC,CAAC;IAED,gCAAgC;IAChC,MAAM,CAAC,KAAK,CAAC,8BAA8B,CAAC,CAAA;IAE5C,MAAM,SAAS,GAAG,MAAM,gBAAgB,CAAC,kBAAkB,CAC1D,QAAQ,EACR,gBAAgB,CAAC,gCAAgC,CAAC,MAAM,CAAC,CACzD,CAAA;IAED,MAAM,CAAC,KAAK,CAAC,8BAA8B,CAAC,CAAA;IAE5C,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAM;QACnC,MAAM,EAAE,MAAM;QAEd,GAAG,EAAE,oCAAoC;QAEzC,MAAM;QAEN,OAAO,EAAE;YACR,eAAe,EAAE,SAAS,OAAO,CAAC,MAAM,EAAE;YAC1C,cAAc,EAAE,YAAY;YAC5B,QAAQ,EAAE,kBAAkB;SAC5B;QAED,IAAI,EAAE,SAAS;QAEf,YAAY,EAAE,MAAM;KACpB,CAAC,CAAA;IAEF,MAAM,gBAAgB,GAAqB,QAAQ,CAAC,IAAI,CAAA;IAExD,MAAM,gBAAgB,GAAG,gBAAgB,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAC,CAAC,EAAE,YAAY,CAAC,CAAC,CAAC,CAAA;IAE/E,yCAAyC;IACzC,MAAM,UAAU,GAAG,gBAAgB,EAAE,UAAU,IAAI,EAAE,CAAA;IAErD,IAAI,QAAQ,GAAa,EAAE,CAAA;IAE3B,qDAAqD;IACrD,MAAM,KAAK,GAAG,gBAAgB,EAAE,KAAK,IAAI,EAAE,CAAA;IAE3C,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACtB,QAAQ,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,IAAuB,EAAiB,EAAE,CAAC,CAAC;YACjE,IAAI,EAAE,MAAM;YACZ,IAAI,EAAE,IAAI,CAAC,IAAI;YACf,SAAS,EAAE,IAAI,CAAC,KAAK;YACrB,OAAO,EAAE,IAAI,CAAC,GAAG;YACjB,UAAU,EAAE,IAAI,CAAC,UAAU;SAC3B,CAAC,CAAC,CAAA;IACJ,CAAC;IAED,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;AAChC,CAAC;AAOD,MAAM,CAAC,MAAM,yBAAyB,GAAuB;IAC5D,MAAM,EAAE,SAAS;IACjB,KAAK,EAAE,QAAQ;CACf,CAAA"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"GoogleCloudSTT.js","sourceRoot":"","sources":["../../src/recognition/GoogleCloudSTT.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,MAAM,QAAQ,CAAA;AAEhC,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAG/C,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAA;AAIrD,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,MAAc,EAAE,YAAY,GAAG,OAAO;IACzF,MAAM,uBAAuB,GAAG,MAAM,gBAAgB,CAAC,kBAAkB,CAAC,QAAQ,EAAE,EAAE,MAAM,EAAE,MAAM,EAAE,UAAU,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,EAAE,CAAC,CAAA;IAEhK,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAC3B,MAAM,CAAC,KAAK,CAAC,uCAAuC,CAAC,CAAA;IAErD,MAAM,WAAW,GAAG;QACnB,MAAM,EAAE;YACP,QAAQ,EAAE,MAAM;YAChB,eAAe,EAAE,KAAK;YACtB,iBAAiB,EAAE,CAAC;YACpB,YAAY;YACZ,wBAAwB,EAAE,EAAE;YAC5B,eAAe,EAAE,CAAC;YAClB,eAAe,EAAE,KAAK;YACtB,qBAAqB,EAAE,IAAI;YAC3B,oBAAoB,EAAE,IAAI;YAC1B,0BAA0B,EAAE,IAAI;YAChC,KAAK,EAAE,aAAa;YACpB,WAAW,EAAE,IAAI;SACjB;QAED,KAAK,EAAE;YACN,OAAO,EAAE,YAAY,CAAC,uBAAuB,CAAC;SAC9C;KACD,CAAA;IAED,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAM;QACnC,MAAM,EAAE,MAAM;QAEd,GAAG,EAAE,0DAA0D;QAE/D,MAAM,EAAE;YACP,KAAK,EAAE,MAAM;SACb;QAED,OAAO,EAAE;YACR,YAAY,EAAE,EAAE;SAChB;QAED,IAAI,EAAE,WAAW;
|
|
1
|
+
{"version":3,"file":"GoogleCloudSTT.js","sourceRoot":"","sources":["../../src/recognition/GoogleCloudSTT.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,MAAM,QAAQ,CAAA;AAEhC,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAG/C,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAA;AAIrD,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,MAAc,EAAE,YAAY,GAAG,OAAO;IACzF,MAAM,uBAAuB,GAAG,MAAM,gBAAgB,CAAC,kBAAkB,CAAC,QAAQ,EAAE,EAAE,MAAM,EAAE,MAAM,EAAE,UAAU,EAAE,KAAK,EAAE,YAAY,EAAE,KAAK,EAAE,YAAY,EAAE,CAAC,EAAE,CAAC,CAAA;IAEhK,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAC3B,MAAM,CAAC,KAAK,CAAC,uCAAuC,CAAC,CAAA;IAErD,MAAM,WAAW,GAAG;QACnB,MAAM,EAAE;YACP,QAAQ,EAAE,MAAM;YAChB,eAAe,EAAE,KAAK;YACtB,iBAAiB,EAAE,CAAC;YACpB,YAAY;YACZ,wBAAwB,EAAE,EAAE;YAC5B,eAAe,EAAE,CAAC;YAClB,eAAe,EAAE,KAAK;YACtB,qBAAqB,EAAE,IAAI;YAC3B,oBAAoB,EAAE,IAAI;YAC1B,0BAA0B,EAAE,IAAI;YAChC,KAAK,EAAE,aAAa;YACpB,WAAW,EAAE,IAAI;SACjB;QAED,KAAK,EAAE;YACN,OAAO,EAAE,YAAY,CAAC,uBAAuB,CAAC;SAC9C;KACD,CAAA;IAED,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAM;QACnC,MAAM,EAAE,MAAM;QAEd,GAAG,EAAE,0DAA0D;QAE/D,MAAM,EAAE;YACP,KAAK,EAAE,MAAM;SACb;QAED,OAAO,EAAE;YACR,YAAY,EAAE,EAAE;SAChB;QAED,IAAI,EAAE,WAAW;QAEjB,YAAY,EAAE,MAAM;KACpB,CAAC,CAAA;IAEF,MAAM,CAAC,KAAK,CAAC,qBAAqB,CAAC,CAAA;IAEnC,MAAM,MAAM,GAAG,iBAAiB,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAA;IAE/C,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,MAAM,CAAA;AACd,CAAC;AAED,SAAS,iBAAiB,CAAC,YAAiB;IAC3C,MAAM,OAAO,GAAG,YAAY,CAAC,OAAO,CAAA;IAEpC,IAAI,UAAU,GAAG,EAAE,CAAA;IACnB,MAAM,QAAQ,GAAa,EAAE,CAAA;IAE7B,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC9B,IAAI,CAAC,MAAM,CAAC,YAAY,IAAI,CAAC,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC,UAAU,EAAE,CAAC;YAC3F,SAAQ;QACT,CAAC;QAED,MAAM,gBAAgB,GAAG,MAAM,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QAE/C,UAAU,IAAI,gBAAgB,CAAC,UAAU,CAAA;QAEzC,KAAK,MAAM,SAAS,IAAI,gBAAgB,CAAC,KAAK,EAAE,CAAC;YAChD,QAAQ,CAAC,IAAI,CAAC;gBACb,IAAI,EAAE,MAAM;gBACZ,IAAI,EAAE,SAAS,CAAC,IAAI;gBACpB,SAAS,EAAE,UAAU,CAAC,SAAS,CAAC,SAAS,CAAC,OAAO,CAAC,GAAG,EAAC,EAAE,CAAC,CAAC;gBAC1D,OAAO,EAAE,UAAU,CAAC,SAAS,CAAC,OAAO,CAAC,OAAO,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC;gBACvD,UAAU,EAAE,SAAS,CAAC,UAAU;aAChC,CAAC,CAAA;QACH,CAAC;IACF,CAAC;IAED,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;AAChC,CAAC"}
|
|
@@ -1,19 +1,19 @@
|
|
|
1
1
|
import { SynthesisVoice } from '../api/API.js';
|
|
2
|
-
export declare function synthesize(text: string, voiceId: string, modelId: string, options:
|
|
2
|
+
export declare function synthesize(text: string, voiceId: string, modelId: string, options: ElevenLabsTTSOptions): Promise<{
|
|
3
3
|
rawAudio: {
|
|
4
4
|
audioChannels: Float32Array<ArrayBufferLike>[];
|
|
5
5
|
sampleRate: number;
|
|
6
6
|
};
|
|
7
7
|
}>;
|
|
8
8
|
export declare function getVoiceList(apiKey: string): Promise<SynthesisVoice[]>;
|
|
9
|
-
export interface
|
|
9
|
+
export interface ElevenLabsTTSOptions {
|
|
10
10
|
apiKey?: string;
|
|
11
11
|
stability?: number;
|
|
12
12
|
similarityBoost?: number;
|
|
13
13
|
style?: number;
|
|
14
14
|
useSpeakerBoost?: boolean;
|
|
15
15
|
}
|
|
16
|
-
export declare const
|
|
16
|
+
export declare const defaultElevenLabsTTSOptions: {
|
|
17
17
|
apiKey: undefined;
|
|
18
18
|
stability: number;
|
|
19
19
|
similarityBoost: number;
|
|
@@ -7,7 +7,7 @@ const log = logToStderr;
|
|
|
7
7
|
export async function synthesize(text, voiceId, modelId, options) {
|
|
8
8
|
const logger = new Logger();
|
|
9
9
|
logger.start('Request synthesis from ElevenLabs');
|
|
10
|
-
options = extendDeep(
|
|
10
|
+
options = extendDeep(defaultElevenLabsTTSOptions, options);
|
|
11
11
|
let response;
|
|
12
12
|
try {
|
|
13
13
|
response = await request({
|
|
@@ -92,7 +92,7 @@ export async function getVoiceList(apiKey) {
|
|
|
92
92
|
});
|
|
93
93
|
return voices;
|
|
94
94
|
}
|
|
95
|
-
export const
|
|
95
|
+
export const defaultElevenLabsTTSOptions = {
|
|
96
96
|
apiKey: undefined,
|
|
97
97
|
stability: 0.5,
|
|
98
98
|
similarityBoost: 0.5,
|
|
@@ -100,4 +100,4 @@ export const defaultElevenlabsTTSOptions = {
|
|
|
100
100
|
useSpeakerBoost: true
|
|
101
101
|
};
|
|
102
102
|
export const supporteMultilingualLanguages = ['zh', 'ko', 'nl', 'tr', 'sv', 'id', 'tl', 'ja', 'uk', 'el', 'cs', 'fi', 'ro', 'ru', 'da', 'bg', 'ms', 'sk', 'hr', 'ar', 'ta', 'pl', 'de', 'es', 'fr', 'it', 'hi', 'pt'];
|
|
103
|
-
//# sourceMappingURL=
|
|
103
|
+
//# sourceMappingURL=ElevenLabsTTS.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"
|
|
1
|
+
{"version":3,"file":"ElevenLabsTTS.js","sourceRoot":"","sources":["../../src/synthesis/ElevenLabsTTS.ts"],"names":[],"mappings":"AAAA,OAAO,EAAkB,OAAO,EAAE,MAAM,QAAQ,CAAA;AAEhD,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAC/C,OAAO,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AACvD,OAAO,EAAE,UAAU,EAAE,MAAM,iCAAiC,CAAA;AAE5D,MAAM,GAAG,GAAG,WAAW,CAAA;AAEvB,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAY,EAAE,OAAe,EAAE,OAAe,EAAE,OAA6B;IAC7G,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAC3B,MAAM,CAAC,KAAK,CAAC,mCAAmC,CAAC,CAAA;IAEjD,OAAO,GAAG,UAAU,CAAC,2BAA2B,EAAE,OAAO,CAAC,CAAA;IAE1D,IAAI,QAA6B,CAAA;IAEjC,IAAI,CAAC;QACJ,QAAQ,GAAG,MAAM,OAAO,CAAM;YAC7B,GAAG,EAAE,+CAA+C,OAAO,EAAE;YAE7D,MAAM,EAAE,MAAM;YAEd,OAAO,EAAE;gBACR,QAAQ,EAAE,YAAY;gBACtB,YAAY,EAAE,OAAO,CAAC,MAAM;aAC5B;YAED,IAAI,EAAE;gBACL,IAAI;gBAEJ,QAAQ,EAAE,OAAO;gBAEjB,aAAa,EAAE;oBACd,SAAS,EAAE,OAAO,CAAC,SAAS;oBAC5B,gBAAgB,EAAE,OAAO,CAAC,eAAe;oBACzC,KAAK,EAAE,OAAO,CAAC,KAAK;oBACpB,iBAAiB,EAAE,OAAO,CAAC,eAAe;iBAC1C;aACD;YAED,YAAY,EAAE,aAAa;SAC3B,CAAC,CAAA;IACH,CAAC;IAAC,OAAO,CAAM,EAAE,CAAC;QACjB,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAA;QAE3B,IAAI,QAAQ,EAAE,CAAC;YACd,MAAM,CAAC,GAAG,CAAC,mCAAmC,QAAQ,CAAC,MAAM,EAAE,CAAC,CAAA;YAEhE,IAAI,QAAQ,CAAC,IAAI,EAAE,CAAC;gBACnB,MAAM,CAAC,GAAG,CAAC,wBAAwB,CAAC,CAAA;gBACpC,MAAM,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAA;YAC1B,CAAC;QACF,CAAC;QAED,MAAM,CAAC,CAAA;IACR,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAA;IACxC,MAAM,QAAQ,GAAG,MAAM,gBAAgB,CAAC,gBAAgB,CAAC,IAAI,UAAU,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAA;IAEvF,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,QAAQ,EAAE,CAAA;AACpB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY,CAAC,MAAc;IAChD,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAM;QACnC,MAAM,EAAE,KAAK;QAEb,GAAG,EAAE,qCAAqC;QAE1C,OAAO,EAAE;YACR,QAAQ,EAAE,0BAA0B;YACpC,YAAY,EAAE,MAAM;SACpB;QAED,YAAY,EAAE,MAAM;KACpB,CAAC,CAAA;IAEF,MAAM,gBAAgB,GAAU,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAA;IAEpD,MAAM,MAAM,GAAqB,gBAAgB,CAAC,GAAG,CAAC,eAAe,CAAC,EAAE;QACvE,MAAM,OAAO,GAAW,eAAe,EAAE,2BAA2B,EAAE,CAAC,CAAC,CAAC,IAAI,uBAAuB,CAAA;QACpG,MAAM,MAAM,GAAuB,eAAe,EAAE,MAAM,EAAE,MAAM,CAAA;QAClE,MAAM,MAAM,GAAgB,eAAe,EAAE,MAAM,EAAE,MAAM,IAAI,SAAS,CAAA;QAExE,MAAM,kBAAkB,GAAa,EAAE,CAAA;QAEvC,IAAI,MAAM,EAAE,CAAC;YACZ,IAAI,MAAM,CAAC,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;gBACnC,kBAAkB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACjC,CAAC;iBAAM,IAAI,MAAM,CAAC,UAAU,CAAC,SAAS,CAAC,EAAE,CAAC;gBACzC,kBAAkB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACjC,CAAC;iBAAM,IAAI,MAAM,KAAK,OAAO,EAAE,CAAC;gBAC/B,kBAAkB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACjC,CAAC;iBAAM,IAAI,MAAM,IAAI,YAAY,EAAE,CAAC;gBACnC,kBAAkB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YACjC,CAAC;QACF,CAAC;QAED,IAAI,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAC,EAAE,CAAC;YACtC,kBAAkB,CAAC,IAAI,CAAC,IAAI,EAAE,GAAG,6BAA6B,CAAC,CAAA;QAChE,CAAC;aAAM,CAAC;YACP,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAC9B,CAAC;QAED,OAAO;YACN,IAAI,EAAE,eAAe,CAAC,IAAI;YAC1B,SAAS,EAAE,kBAAkB;YAC7B,MAAM;YAEN,iBAAiB,EAAE,eAAe,CAAC,QAAQ;YAC3C,iBAAiB,EAAE,OAAO;SAC1B,CAAA;IACF,CAAC,CAAC,CAAA;IAEF,OAAO,MAAM,CAAA;AACd,CAAC;AAUD,MAAM,CAAC,MAAM,2BAA2B,GAAG;IAC1C,MAAM,EAAE,SAAS;IACjB,SAAS,EAAE,GAAG;IACd,eAAe,EAAE,GAAG;IACpB,KAAK,EAAE,CAAC;IACR,eAAe,EAAE,IAAI;CACrB,CAAA;AAED,MAAM,CAAC,MAAM,6BAA6B,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAA"}
|
|
@@ -52,4 +52,4 @@ export interface EspeakOptions {
|
|
|
52
52
|
insertSeparators: boolean;
|
|
53
53
|
}
|
|
54
54
|
export declare const defaultEspeakOptions: EspeakOptions;
|
|
55
|
-
export declare function testKirshenbaumPhonemization(text: string): Promise<void>;
|
|
55
|
+
export declare function testKirshenbaumPhonemization(text: string, language?: string): Promise<void>;
|