echogarden 0.12.2 → 1.0.0

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.
Files changed (334) hide show
  1. package/README.md +15 -14
  2. package/data/schemas/options.json +398 -111
  3. package/dist/alignment/DTWMfccSequenceAlignment.d.ts +1 -1
  4. package/dist/alignment/DTWMfccSequenceAlignment.js +8 -8
  5. package/dist/alignment/DTWSequenceAlignment.d.ts +1 -1
  6. package/dist/alignment/DTWSequenceAlignment.js +1 -1
  7. package/dist/alignment/DTWSequenceAlignmentWindowed.d.ts +1 -1
  8. package/dist/alignment/DTWSequenceAlignmentWindowed.js +2 -2
  9. package/dist/alignment/LevenshteinSequenceAlignment.d.ts +1 -1
  10. package/dist/alignment/LevenshteinSequenceAlignment.js +1 -1
  11. package/dist/alignment/SpeechAlignment.d.ts +9 -10
  12. package/dist/alignment/SpeechAlignment.js +136 -105
  13. package/dist/alignment/SpeechAlignment.js.map +1 -1
  14. package/dist/api/API.d.ts +13 -12
  15. package/dist/api/API.js +14 -13
  16. package/dist/api/API.js.map +1 -1
  17. package/dist/api/APIOptions.d.ts +5 -4
  18. package/dist/api/Alignment.d.ts +15 -9
  19. package/dist/api/Alignment.js +88 -74
  20. package/dist/api/Alignment.js.map +1 -1
  21. package/dist/api/Common.js +1 -1
  22. package/dist/api/Denoising.d.ts +6 -6
  23. package/dist/api/Denoising.js +23 -23
  24. package/dist/api/Denoising.js.map +1 -1
  25. package/dist/api/LanguageDetection.d.ts +19 -12
  26. package/dist/api/LanguageDetection.js +88 -38
  27. package/dist/api/LanguageDetection.js.map +1 -1
  28. package/dist/api/Recognition.d.ts +16 -6
  29. package/dist/api/Recognition.js +129 -55
  30. package/dist/api/Recognition.js.map +1 -1
  31. package/dist/api/SourceSeparation.d.ts +17 -0
  32. package/dist/api/SourceSeparation.js +61 -0
  33. package/dist/api/SourceSeparation.js.map +1 -0
  34. package/dist/api/Synthesis.d.ts +18 -18
  35. package/dist/api/Synthesis.js +191 -164
  36. package/dist/api/Synthesis.js.map +1 -1
  37. package/dist/api/Translation.d.ts +19 -8
  38. package/dist/api/Translation.js +132 -35
  39. package/dist/api/Translation.js.map +1 -1
  40. package/dist/api/Vad.d.ts +10 -5
  41. package/dist/api/Vad.js +76 -38
  42. package/dist/api/Vad.js.map +1 -1
  43. package/dist/audio/AudioBufferConversion.d.ts +1 -1
  44. package/dist/audio/AudioBufferConversion.js +4 -4
  45. package/dist/audio/AudioPlayer.d.ts +1 -1
  46. package/dist/audio/AudioPlayer.js +26 -26
  47. package/dist/audio/AudioPlayer.js.map +1 -1
  48. package/dist/audio/AudioRecorder.d.ts +1 -1
  49. package/dist/audio/AudioRecorder.js +5 -5
  50. package/dist/audio/AudioUtilities.d.ts +13 -9
  51. package/dist/audio/AudioUtilities.js +86 -24
  52. package/dist/audio/AudioUtilities.js.map +1 -1
  53. package/dist/cli/CLI.d.ts +3 -3
  54. package/dist/cli/CLI.js +271 -162
  55. package/dist/cli/CLI.js.map +1 -1
  56. package/dist/cli/CLIConfigFile.js +8 -8
  57. package/dist/cli/CLILauncher.js +6 -6
  58. package/dist/cli/CLIOptionsSchema.js +2 -2
  59. package/dist/cli/CLIParser.js +5 -5
  60. package/dist/cli/CLIStarter.js +4 -4
  61. package/dist/codecs/FFMpegTranscoder.d.ts +2 -2
  62. package/dist/codecs/FFMpegTranscoder.js +37 -37
  63. package/dist/codecs/FFMpegTranscoder.js.map +1 -1
  64. package/dist/codecs/TIMITCodec.js +5 -5
  65. package/dist/codecs/WaveCodec.d.ts +1 -1
  66. package/dist/codecs/WaveCodec.js +22 -22
  67. package/dist/denoising/RNNoise.d.ts +1 -1
  68. package/dist/denoising/RNNoise.js +9 -9
  69. package/dist/dsp/BiquadFilter.d.ts +3 -2
  70. package/dist/dsp/BiquadFilter.js +18 -11
  71. package/dist/dsp/BiquadFilter.js.map +1 -1
  72. package/dist/dsp/DecayingPeakEstimator.d.ts +16 -0
  73. package/dist/dsp/DecayingPeakEstimator.js +23 -0
  74. package/dist/dsp/DecayingPeakEstimator.js.map +1 -0
  75. package/dist/dsp/FFT.d.ts +8 -4
  76. package/dist/dsp/FFT.js +76 -30
  77. package/dist/dsp/FFT.js.map +1 -1
  78. package/dist/dsp/KWeightingFilter.d.ts +9 -0
  79. package/dist/dsp/KWeightingFilter.js +40 -0
  80. package/dist/dsp/KWeightingFilter.js.map +1 -0
  81. package/dist/dsp/LoudnessEstimator.d.ts +21 -0
  82. package/dist/dsp/LoudnessEstimator.js +47 -0
  83. package/dist/dsp/LoudnessEstimator.js.map +1 -0
  84. package/dist/dsp/MFCC.d.ts +2 -2
  85. package/dist/dsp/MFCC.js +15 -15
  86. package/dist/dsp/MelSpectogram.d.ts +1 -1
  87. package/dist/dsp/MelSpectogram.js +6 -6
  88. package/dist/dsp/Rubberband.d.ts +11 -11
  89. package/dist/dsp/Rubberband.js +27 -27
  90. package/dist/dsp/Sonic.d.ts +1 -1
  91. package/dist/dsp/Sonic.js +3 -3
  92. package/dist/dsp/SpeexResampler.d.ts +1 -1
  93. package/dist/dsp/SpeexResampler.js +2 -2
  94. package/dist/math/VectorMath.d.ts +12 -8
  95. package/dist/math/VectorMath.js +35 -32
  96. package/dist/math/VectorMath.js.map +1 -1
  97. package/dist/nlp/ChineseSegmentation.js +2 -2
  98. package/dist/nlp/CompromiseNLP.js +3 -3
  99. package/dist/nlp/EspeakPhonemizer.js +30 -30
  100. package/dist/nlp/IPA.js +20 -20
  101. package/dist/nlp/JapaneseSegmentation.js +6 -6
  102. package/dist/nlp/Lexicon.d.ts +1 -1
  103. package/dist/nlp/Lexicon.js +7 -7
  104. package/dist/nlp/Segmentation.d.ts +3 -0
  105. package/dist/nlp/Segmentation.js +21 -14
  106. package/dist/nlp/Segmentation.js.map +1 -1
  107. package/dist/nlp/TextNormalizer.js +16 -16
  108. package/dist/recognition/AmazonTranscribeSTT.d.ts +2 -2
  109. package/dist/recognition/AmazonTranscribeSTT.js +13 -14
  110. package/dist/recognition/AmazonTranscribeSTT.js.map +1 -1
  111. package/dist/recognition/AzureCognitiveServicesSTT.js +5 -6
  112. package/dist/recognition/AzureCognitiveServicesSTT.js.map +1 -1
  113. package/dist/recognition/GoogleCloudSTT.d.ts +3 -3
  114. package/dist/recognition/GoogleCloudSTT.js +18 -18
  115. package/dist/recognition/OpenAICloudSTT.d.ts +19 -0
  116. package/dist/recognition/OpenAICloudSTT.js +81 -0
  117. package/dist/recognition/OpenAICloudSTT.js.map +1 -0
  118. package/dist/recognition/SileroSTT.d.ts +2 -2
  119. package/dist/recognition/SileroSTT.js +25 -25
  120. package/dist/recognition/VoskSTT.d.ts +2 -2
  121. package/dist/recognition/VoskSTT.js +8 -8
  122. package/dist/recognition/WhisperCppSTT.d.ts +88 -0
  123. package/dist/recognition/WhisperCppSTT.js +332 -0
  124. package/dist/recognition/WhisperCppSTT.js.map +1 -0
  125. package/dist/recognition/WhisperSTT.d.ts +49 -25
  126. package/dist/recognition/WhisperSTT.js +626 -481
  127. package/dist/recognition/WhisperSTT.js.map +1 -1
  128. package/dist/server/Client.d.ts +1 -1
  129. package/dist/server/Client.js +22 -22
  130. package/dist/server/Server.js +9 -9
  131. package/dist/server/Server.js.map +1 -1
  132. package/dist/server/Worker.d.ts +22 -22
  133. package/dist/server/Worker.js +36 -36
  134. package/dist/server/Worker.js.map +1 -1
  135. package/dist/server/WorkerStarter.js +2 -2
  136. package/dist/source-separation/MDXNetSourceSeparation.d.ts +11 -0
  137. package/dist/source-separation/MDXNetSourceSeparation.js +161 -0
  138. package/dist/source-separation/MDXNetSourceSeparation.js.map +1 -0
  139. package/dist/speech-language-detection/SileroLanguageDetection.d.ts +1 -1
  140. package/dist/speech-language-detection/SileroLanguageDetection.js +7 -7
  141. package/dist/subtitles/Subtitles.d.ts +10 -0
  142. package/dist/subtitles/Subtitles.js +2 -2
  143. package/dist/subtitles/Subtitles.js.map +1 -1
  144. package/dist/synthesis/AwsPollyTTS.d.ts +1 -1
  145. package/dist/synthesis/AwsPollyTTS.js +12 -12
  146. package/dist/synthesis/AzureCognitiveServicesTTS.js +7 -7
  147. package/dist/synthesis/CoquiServerTTS.js +10 -10
  148. package/dist/synthesis/CoquiServerTTS.js.map +1 -1
  149. package/dist/synthesis/ElevenlabsTTS.d.ts +23 -0
  150. package/dist/synthesis/ElevenlabsTTS.js +103 -0
  151. package/dist/synthesis/ElevenlabsTTS.js.map +1 -0
  152. package/dist/synthesis/EspeakTTS.d.ts +6 -5
  153. package/dist/synthesis/EspeakTTS.js +81 -69
  154. package/dist/synthesis/EspeakTTS.js.map +1 -1
  155. package/dist/synthesis/FliteTTS.d.ts +3 -3
  156. package/dist/synthesis/FliteTTS.js +154 -154
  157. package/dist/synthesis/FliteTTS.js.map +1 -1
  158. package/dist/synthesis/GoogleCloudTTS.d.ts +3 -3
  159. package/dist/synthesis/GoogleCloudTTS.js +17 -17
  160. package/dist/synthesis/GoogleCloudTTS.js.map +1 -1
  161. package/dist/synthesis/GoogleTranslateTTS.d.ts +1 -1
  162. package/dist/synthesis/GoogleTranslateTTS.js +103 -103
  163. package/dist/synthesis/MicrosoftEdgeTTS.d.ts +2 -2
  164. package/dist/synthesis/MicrosoftEdgeTTS.js +74 -74
  165. package/dist/synthesis/OpenAICloudTTS.d.ts +13 -0
  166. package/dist/synthesis/OpenAICloudTTS.js +169 -0
  167. package/dist/synthesis/OpenAICloudTTS.js.map +1 -0
  168. package/dist/synthesis/SamTTS.js +3 -3
  169. package/dist/synthesis/SapiTTS.d.ts +3 -3
  170. package/dist/synthesis/SapiTTS.js +26 -26
  171. package/dist/synthesis/StreamlabsPollyTTS.d.ts +2 -2
  172. package/dist/synthesis/StreamlabsPollyTTS.js +27 -27
  173. package/dist/synthesis/SvoxPicoTTS.d.ts +2 -2
  174. package/dist/synthesis/SvoxPicoTTS.js +65 -65
  175. package/dist/synthesis/SvoxPicoTTS.js.map +1 -1
  176. package/dist/synthesis/VitsTTS.d.ts +3 -3
  177. package/dist/synthesis/VitsTTS.js +378 -378
  178. package/dist/synthesis/VitsTTS.js.map +1 -1
  179. package/dist/tests/Test.js +2 -2
  180. package/dist/utilities/Compression.d.ts +5 -0
  181. package/dist/utilities/Compression.js +29 -13
  182. package/dist/utilities/Compression.js.map +1 -1
  183. package/dist/utilities/FileDownloader.d.ts +1 -1
  184. package/dist/utilities/FileDownloader.js +16 -16
  185. package/dist/utilities/FileSystem.js +7 -7
  186. package/dist/utilities/Locale.d.ts +7 -7
  187. package/dist/utilities/Locale.js +15 -15
  188. package/dist/utilities/Logger.js +3 -3
  189. package/dist/utilities/ObjectUtilities.js +19 -19
  190. package/dist/utilities/OpenPromise.js +2 -2
  191. package/dist/utilities/OpenPromise.js.map +1 -1
  192. package/dist/utilities/PackageManager.js +31 -0
  193. package/dist/utilities/PackageManager.js.map +1 -1
  194. package/dist/utilities/PathUtilities.js +8 -8
  195. package/dist/utilities/RandomGenerator.js +2 -2
  196. package/dist/utilities/SmoothEstimator.d.ts +8 -0
  197. package/dist/utilities/SmoothEstimator.js +25 -0
  198. package/dist/utilities/SmoothEstimator.js.map +1 -0
  199. package/dist/utilities/TarballMaker.js +8 -8
  200. package/dist/utilities/Timeline.d.ts +3 -2
  201. package/dist/utilities/Timeline.js +11 -11
  202. package/dist/utilities/Timeline.js.map +1 -1
  203. package/dist/utilities/Timer.js +4 -4
  204. package/dist/utilities/Utilities.d.ts +4 -0
  205. package/dist/utilities/Utilities.js +38 -15
  206. package/dist/utilities/Utilities.js.map +1 -1
  207. package/dist/utilities/WasmMemoryManager.js +7 -7
  208. package/dist/utilities/WebReader.js +23 -23
  209. package/dist/utilities/WikipediaReader.js +2 -2
  210. package/dist/voice-activity-detection/AdaptiveGateVAD.d.ts +28 -0
  211. package/dist/voice-activity-detection/AdaptiveGateVAD.js +138 -0
  212. package/dist/voice-activity-detection/AdaptiveGateVAD.js.map +1 -0
  213. package/dist/voice-activity-detection/SileroVAD.d.ts +1 -1
  214. package/dist/voice-activity-detection/SileroVAD.js +5 -5
  215. package/dist/voice-activity-detection/SileroVAD.js.map +1 -1
  216. package/dist/voice-activity-detection/WebRtcVAD.d.ts +1 -1
  217. package/dist/voice-activity-detection/WebRtcVAD.js +4 -4
  218. package/docs/API.md +29 -11
  219. package/docs/CLI.md +31 -7
  220. package/docs/Contributing.md +38 -0
  221. package/docs/Development.md +93 -19
  222. package/docs/Engines.md +28 -16
  223. package/docs/Licenses.md +4 -1
  224. package/docs/Options.md +158 -78
  225. package/docs/Releases.md +262 -0
  226. package/docs/Server.md +7 -7
  227. package/docs/Tasklist.md +95 -76
  228. package/docs/Technical.md +4 -4
  229. package/package.json +13 -14
  230. package/src/alignment/DTWMfccSequenceAlignment.ts +9 -9
  231. package/src/alignment/DTWSequenceAlignment.ts +2 -2
  232. package/src/alignment/DTWSequenceAlignmentWindowed.ts +3 -3
  233. package/src/alignment/LevenshteinSequenceAlignment.ts +2 -2
  234. package/src/alignment/SpeechAlignment.ts +204 -119
  235. package/src/api/API.ts +14 -13
  236. package/src/api/APIOptions.ts +12 -11
  237. package/src/api/Alignment.ts +147 -90
  238. package/src/api/Common.ts +1 -1
  239. package/src/api/Denoising.ts +28 -28
  240. package/src/api/LanguageDetection.ts +135 -48
  241. package/src/api/Recognition.ts +198 -59
  242. package/src/api/SourceSeparation.ts +99 -0
  243. package/src/api/Synthesis.ts +217 -181
  244. package/src/api/Translation.ts +193 -40
  245. package/src/api/Vad.ts +110 -41
  246. package/src/audio/AudioBufferConversion.ts +4 -4
  247. package/src/audio/AudioPlayer.ts +27 -27
  248. package/src/audio/AudioRecorder.ts +5 -5
  249. package/src/audio/AudioUtilities.ts +107 -24
  250. package/src/cli/CLI.ts +313 -164
  251. package/src/cli/CLIConfigFile.ts +8 -8
  252. package/src/cli/CLILauncher.ts +6 -6
  253. package/src/cli/CLIOptionsSchema.ts +2 -2
  254. package/src/cli/CLIParser.ts +5 -5
  255. package/src/cli/CLIStarter.ts +4 -4
  256. package/src/codecs/FFMpegTranscoder.ts +38 -38
  257. package/src/codecs/TIMITCodec.ts +5 -5
  258. package/src/codecs/WaveCodec.ts +22 -22
  259. package/src/denoising/RNNoise.ts +9 -9
  260. package/src/dsp/BiquadFilter.ts +19 -11
  261. package/src/dsp/DecayingPeakEstimator.ts +35 -0
  262. package/src/dsp/FFT.ts +103 -35
  263. package/src/dsp/KWeightingFilter.ts +43 -0
  264. package/src/dsp/LoudnessEstimator.ts +74 -0
  265. package/src/dsp/MFCC.ts +15 -15
  266. package/src/dsp/MelSpectogram.ts +7 -7
  267. package/src/dsp/Rubberband.ts +38 -38
  268. package/src/dsp/Sonic.ts +4 -4
  269. package/src/dsp/SpeexResampler.ts +2 -2
  270. package/src/math/VectorMath.ts +42 -33
  271. package/src/nlp/ChineseSegmentation.ts +3 -3
  272. package/src/nlp/CompromiseNLP.ts +3 -3
  273. package/src/nlp/EspeakPhonemizer.ts +30 -30
  274. package/src/nlp/IPA.ts +20 -20
  275. package/src/nlp/JapaneseSegmentation.ts +6 -6
  276. package/src/nlp/Lexicon.ts +8 -8
  277. package/src/nlp/Segmentation.ts +23 -14
  278. package/src/nlp/TextNormalizer.ts +16 -16
  279. package/src/recognition/AmazonTranscribeSTT.ts +16 -17
  280. package/src/recognition/AzureCognitiveServicesSTT.ts +8 -6
  281. package/src/recognition/GoogleCloudSTT.ts +21 -21
  282. package/src/recognition/OpenAICloudSTT.ts +142 -0
  283. package/src/recognition/SileroSTT.ts +26 -26
  284. package/src/recognition/VoskSTT.ts +10 -10
  285. package/src/recognition/WhisperCppSTT.ts +555 -0
  286. package/src/recognition/WhisperSTT.ts +760 -507
  287. package/src/server/Client.ts +23 -23
  288. package/src/server/Server.ts +9 -9
  289. package/src/server/Worker.ts +53 -53
  290. package/src/server/WorkerStarter.ts +2 -2
  291. package/src/source-separation/MDXNetSourceSeparation.ts +228 -0
  292. package/src/speech-language-detection/SileroLanguageDetection.ts +8 -8
  293. package/src/subtitles/Subtitles.ts +3 -3
  294. package/src/synthesis/AwsPollyTTS.ts +14 -14
  295. package/src/synthesis/AzureCognitiveServicesTTS.ts +10 -10
  296. package/src/synthesis/CoquiServerTTS.ts +10 -10
  297. package/src/synthesis/ElevenlabsTTS.ts +137 -0
  298. package/src/synthesis/EspeakTTS.ts +90 -71
  299. package/src/synthesis/FliteTTS.ts +157 -157
  300. package/src/synthesis/GoogleCloudTTS.ts +19 -19
  301. package/src/synthesis/GoogleTranslateTTS.ts +104 -104
  302. package/src/synthesis/MicrosoftEdgeTTS.ts +80 -80
  303. package/src/synthesis/OpenAICloudTTS.ts +196 -0
  304. package/src/synthesis/SamTTS.ts +3 -3
  305. package/src/synthesis/SapiTTS.ts +29 -29
  306. package/src/synthesis/StreamlabsPollyTTS.ts +29 -29
  307. package/src/synthesis/SvoxPicoTTS.ts +67 -67
  308. package/src/synthesis/VitsTTS.ts +380 -380
  309. package/src/tests/Test.ts +4 -4
  310. package/src/utilities/Compression.ts +34 -13
  311. package/src/utilities/FileDownloader.ts +19 -19
  312. package/src/utilities/FileSystem.ts +7 -7
  313. package/src/utilities/Locale.ts +22 -22
  314. package/src/utilities/Logger.ts +4 -4
  315. package/src/utilities/ObjectUtilities.ts +19 -19
  316. package/src/utilities/OpenPromise.ts +2 -2
  317. package/src/utilities/PackageManager.ts +40 -0
  318. package/src/utilities/PathUtilities.ts +8 -8
  319. package/src/utilities/RandomGenerator.ts +3 -3
  320. package/src/utilities/SmoothEstimator.ts +35 -0
  321. package/src/utilities/TarballMaker.ts +9 -9
  322. package/src/utilities/Timeline.ts +15 -13
  323. package/src/utilities/Timer.ts +4 -4
  324. package/src/utilities/Utilities.ts +49 -15
  325. package/src/utilities/WasmMemoryManager.ts +7 -7
  326. package/src/utilities/WebReader.ts +23 -23
  327. package/src/utilities/WikipediaReader.ts +2 -2
  328. package/src/voice-activity-detection/AdaptiveGateVAD.ts +202 -0
  329. package/src/voice-activity-detection/SileroVAD.ts +5 -5
  330. package/src/voice-activity-detection/WebRtcVAD.ts +5 -5
  331. package/dist/synthesis/ElevenLabsTTS.d.ts +0 -8
  332. package/dist/synthesis/ElevenLabsTTS.js +0 -82
  333. package/dist/synthesis/ElevenLabsTTS.js.map +0 -1
  334. package/src/synthesis/ElevenLabsTTS.ts +0 -104
@@ -1,10 +1,12 @@
1
1
  import { ParagraphBreakType, WhitespaceProcessing } from '../api/Common.js';
2
2
  export declare const wordCharacterPattern: RegExp;
3
+ export declare const punctuationPattern: RegExp;
3
4
  export declare const phraseSeparators: string[];
4
5
  export declare const sentenceSeparators: string[];
5
6
  export declare const symbolWords: string[];
6
7
  export declare function isWordOrSymbolWord(str: string): boolean;
7
8
  export declare function isWord(str: string): boolean;
9
+ export declare function isPunctuation(str: string): boolean;
8
10
  export declare class Sentence {
9
11
  phrases: Phrase[];
10
12
  readonly isSentenceFinalizer = true;
@@ -41,3 +43,4 @@ export declare function parse(text: string, langCode: string): Promise<Sentence[
41
43
  export declare function splitToSentences(text: string, langCode: string): string[];
42
44
  export declare function splitToWords(text: string, langCode: string): Promise<string[]>;
43
45
  export declare function splitToParagraphs(text: string, paragraphBreaks: ParagraphBreakType, whitespace: WhitespaceProcessing): string[];
46
+ export declare function splitToLines(text: string): string[];
@@ -5,9 +5,10 @@ import { getShortLanguageCode } from '../utilities/Locale.js';
5
5
  import { splitJapaneseTextToWords_Kuromoji } from './JapaneseSegmentation.js';
6
6
  const log = logToStderr;
7
7
  export const wordCharacterPattern = /[\p{Letter}\p{Number}]/u;
8
- export const phraseSeparators = [",", ";", ":"];
9
- export const sentenceSeparators = [".", "?", "!"];
10
- export const symbolWords = ["$", "€", "¢", "£", "¥", "©", "®", "™", "%", "&", "#", "~", "@", "+", "±", "÷", "/", "*", "=", "¼", "½", "¾"];
8
+ export const punctuationPattern = /[\p{Punctuation}]/u;
9
+ export const phraseSeparators = [',', ';', ':'];
10
+ export const sentenceSeparators = ['.', '?', '!'];
11
+ export const symbolWords = ['$', '€', '¢', '£', '¥', '©', '®', '™', '%', '&', '#', '~', '@', '+', '±', '÷', '/', '*', '=', '¼', '½', '¾'];
11
12
  export function isWordOrSymbolWord(str) {
12
13
  return isWord(str) || symbolWords.includes(str);
13
14
  }
@@ -15,16 +16,19 @@ export function isWord(str) {
15
16
  str = str.trim();
16
17
  return wordCharacterPattern.test(str) || symbolWords.includes(str);
17
18
  }
19
+ export function isPunctuation(str) {
20
+ return punctuationPattern.test(str);
21
+ }
18
22
  export class Sentence {
19
23
  phrases = [];
20
24
  isSentenceFinalizer = true;
21
25
  get length() { return sumArray(this.phrases, (phrase) => phrase.length); }
22
- get text() { return this.phrases.reduce((result, phrase) => result + phrase.text, ""); }
26
+ get text() { return this.phrases.reduce((result, phrase) => result + phrase.text, ''); }
23
27
  }
24
28
  export class Phrase {
25
29
  words = [];
26
30
  get length() { return sumArray(this.words, (word) => word.length); }
27
- get text() { return this.words.reduce((result, word) => result + word.text, ""); }
31
+ get text() { return this.words.reduce((result, word) => result + word.text, ''); }
28
32
  get lastWord() {
29
33
  if (this.words.length == 0) {
30
34
  return undefined;
@@ -48,7 +52,7 @@ export class Word {
48
52
  export class Fragment {
49
53
  segments = [];
50
54
  get length() { return sumArray(this.segments, (phrase) => phrase.length); }
51
- get text() { return this.segments.reduce((result, segment) => result + segment.text, ""); }
55
+ get text() { return this.segments.reduce((result, segment) => result + segment.text, ''); }
52
56
  get isEmpty() { return this.length == 0; }
53
57
  get isNonempty() { return !this.isEmpty; }
54
58
  get lastSegment() {
@@ -139,15 +143,15 @@ export async function parse(text, langCode) {
139
143
  return sentences;
140
144
  }
141
145
  export function splitToSentences(text, langCode) {
142
- const shortLangCode = getShortLanguageCode(langCode || "");
146
+ const shortLangCode = getShortLanguageCode(langCode || '');
143
147
  return CldrSegmentation.sentenceSplit(text, CldrSegmentation.suppressions[shortLangCode]);
144
148
  }
145
149
  export async function splitToWords(text, langCode) {
146
- const shortLangCode = getShortLanguageCode(langCode || "");
147
- if (shortLangCode == "zh" || shortLangCode == "cmn") {
150
+ const shortLangCode = getShortLanguageCode(langCode || '');
151
+ if (shortLangCode == 'zh' || shortLangCode == 'cmn') {
148
152
  return splitChineseTextToWords_Jieba(text, undefined, true);
149
153
  }
150
- else if (shortLangCode == "ja") {
154
+ else if (shortLangCode == 'ja') {
151
155
  return splitJapaneseTextToWords_Kuromoji(text);
152
156
  }
153
157
  else {
@@ -165,14 +169,17 @@ export function splitToParagraphs(text, paragraphBreaks, whitespace) {
165
169
  else {
166
170
  throw new Error(`Invalid paragraph break type: ${paragraphBreaks}`);
167
171
  }
168
- if (whitespace == "removeLineBreaks") {
169
- paragraphs = paragraphs.map(p => p.replaceAll(/(\r?\n)+/g, " "));
172
+ if (whitespace == 'removeLineBreaks') {
173
+ paragraphs = paragraphs.map(p => p.replaceAll(/(\r?\n)+/g, ' '));
170
174
  }
171
- else if (whitespace == "collapse") {
172
- paragraphs = paragraphs.map(p => p.replaceAll(/\s+/g, " "));
175
+ else if (whitespace == 'collapse') {
176
+ paragraphs = paragraphs.map(p => p.replaceAll(/\s+/g, ' '));
173
177
  }
174
178
  paragraphs = paragraphs.map(p => p.trim());
175
179
  paragraphs = paragraphs.filter(p => p.length > 0);
176
180
  return paragraphs;
177
181
  }
182
+ export function splitToLines(text) {
183
+ return text.split(/\r?\n/g);
184
+ }
178
185
  //# sourceMappingURL=Segmentation.js.map
@@ -1 +1 @@
1
- {"version":3,"file":"Segmentation.js","sourceRoot":"","sources":["../../src/nlp/Segmentation.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,gBAAgB,MAAM,mBAAmB,CAAA;AACrD,OAAO,EAAE,6BAA6B,EAAE,MAAM,0BAA0B,CAAA;AAExE,OAAO,EAAE,QAAQ,EAAE,aAAa,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AAC9F,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAA;AAC7D,OAAO,EAAE,iCAAiC,EAAE,MAAM,2BAA2B,CAAA;AAG7E,MAAM,GAAG,GAAG,WAAW,CAAA;AAEvB,MAAM,CAAC,MAAM,oBAAoB,GAAG,yBAAyB,CAAA;AAC7D,MAAM,CAAC,MAAM,gBAAgB,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAA;AAC/C,MAAM,CAAC,MAAM,kBAAkB,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAA;AACjD,MAAM,CAAC,MAAM,WAAW,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAA;AAEzI,MAAM,UAAU,kBAAkB,CAAC,GAAW;IAC7C,OAAO,MAAM,CAAC,GAAG,CAAC,IAAI,WAAW,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAA;AAChD,CAAC;AAED,MAAM,UAAU,MAAM,CAAC,GAAW;IACjC,GAAG,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;IAChB,OAAO,oBAAoB,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,WAAW,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAA;AACnE,CAAC;AAED,MAAM,OAAO,QAAQ;IACpB,OAAO,GAAa,EAAE,CAAA;IAEb,mBAAmB,GAAG,IAAI,CAAA;IAEnC,IAAI,MAAM,KAAK,OAAO,QAAQ,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,MAAM,CAAC,CAAA,CAAC,CAAC;IAEzE,IAAI,IAAI,KAAK,OAAO,IAAI,CAAC,OAAO,CAAC,MAAM,CAAS,CAAC,MAAM,EAAE,MAAM,EAAE,EAAE,CAAC,MAAM,GAAG,MAAM,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA,CAAC,CAAC;CAC/F;AAED,MAAM,OAAO,MAAM;IAClB,KAAK,GAAW,EAAE,CAAA;IAElB,IAAI,MAAM,KAAK,OAAO,QAAQ,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA,CAAC,CAAC;IAEnE,IAAI,IAAI,KAAK,OAAO,IAAI,CAAC,KAAK,CAAC,MAAM,CAAS,CAAC,MAAM,EAAE,IAAI,EAAE,EAAE,CAAC,MAAM,GAAG,IAAI,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA,CAAC,CAAC;IAEzF,IAAI,QAAQ;QACX,IAAI,IAAI,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;YAC5B,OAAO,SAAS,CAAA;QACjB,CAAC;QAED,OAAO,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IACzC,CAAC;IAED,IAAI,mBAAmB,KAAK,OAAO,IAAI,CAAC,QAAQ,IAAI,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,mBAAmB,CAAC,CAAC,CAAC,KAAK,CAAA,CAAC,CAAC;CACtG;AAED,MAAM,OAAO,IAAI;IACP,IAAI,CAAQ;IACrB,mBAAmB,CAAS;IAE5B,YAAY,IAAY,EAAE,mBAA4B;QACrD,IAAI,CAAC,IAAI,GAAG,IAAI,CAAA;QAChB,IAAI,CAAC,mBAAmB,GAAG,mBAAmB,CAAA;IAC/C,CAAC;IAED,IAAI,uBAAuB,KAAK,OAAO,CAAC,oBAAoB,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,YAAY,CAAA,CAAC,CAAC;IAEpG,IAAI,YAAY,KAAK,OAAO,WAAW,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA,CAAC,CAAC;IAE7D,IAAI,iBAAiB,KAAK,OAAO,IAAI,CAAC,uBAAuB,IAAI,aAAa,CAAC,IAAI,CAAC,IAAI,EAAE,gBAAgB,CAAC,CAAA,CAAC,CAAC;IAE7G,IAAI,MAAM,KAAK,OAAO,IAAI,CAAC,IAAI,CAAC,MAAM,CAAA,CAAC,CAAC;CACxC;AAID,MAAM,OAAO,QAAQ;IACpB,QAAQ,GAAc,EAAE,CAAA;IAExB,IAAI,MAAM,KAAK,OAAO,QAAQ,CAAC,IAAI,CAAC,QAAQ,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,MAAM,CAAC,CAAA,CAAC,CAAC;IAE1E,IAAI,IAAI,KAAK,OAAO,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAS,CAAC,MAAM,EAAE,OAAO,EAAE,EAAE,CAAC,MAAM,GAAG,OAAO,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA,CAAC,CAAC;IAElG,IAAI,OAAO,KAAK,OAAO,IAAI,CAAC,MAAM,IAAI,CAAC,CAAA,CAAC,CAAC;IAEzC,IAAI,UAAU,KAAK,OAAO,CAAC,IAAI,CAAC,OAAO,CAAA,CAAC,CAAC;IAEzC,IAAI,WAAW;QACd,IAAI,IAAI,CAAC,OAAO,EAAE,CAAC;YAClB,OAAO,SAAS,CAAA;QACjB,CAAC;QAED,OAAO,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IAC/C,CAAC;CACD;AAED,MAAM,CAAC,KAAK,UAAU,gBAAgB,CAAC,IAAY,EAAE,iBAAyB,EAAE,QAAgB,EAAE,iBAAiB,GAAG,IAAI,EAAE,eAAe,GAAG,IAAI;IACjJ,MAAM,UAAU,GAAG,MAAM,KAAK,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAA;IAE9C,MAAM,SAAS,GAAe,EAAE,CAAA;IAChC,IAAI,eAAe,GAAG,IAAI,QAAQ,EAAE,CAAA;IAEpC,MAAM,oCAAoC,GAAG,GAAG,EAAE,CAAC,iBAAiB,GAAG,eAAe,CAAC,MAAM,CAAA;IAC7F,MAAM,yBAAyB,GAAG,GAAG,EAAE;QACtC,IAAI,eAAe,CAAC,UAAU,EAAE,CAAC;YAChC,SAAS,CAAC,IAAI,CAAC,eAAe,CAAC,CAAA;YAC/B,eAAe,GAAG,IAAI,QAAQ,EAAE,CAAA;QACjC,CAAC;IACF,CAAC,CAAA;IAED,MAAM,mBAAmB,GAAG,CAAC,OAAgB,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,IAAI,oCAAoC,EAAE,CAAA;IAE1G,KAAK,MAAM,QAAQ,IAAI,UAAU,EAAE,CAAC;QACnC,IAAI,mBAAmB,CAAC,QAAQ,CAAC,EAAE,CAAC;YACnC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;YACvC,SAAQ;QACT,CAAC;QAED,IAAI,iBAAiB,EAAE,CAAC;YACvB,yBAAyB,EAAE,CAAA;YAE3B,IAAI,mBAAmB,CAAC,QAAQ,CAAC,EAAE,CAAC;gBACnC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;gBACvC,SAAQ;YACT,CAAC;QACF,CAAC;QAED,KAAK,MAAM,MAAM,IAAI,QAAQ,CAAC,OAAO,EAAE,CAAC;YACvC,IAAI,mBAAmB,CAAC,MAAM,CAAC,EAAE,CAAC;gBACjC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;gBACrC,SAAQ;YACT,CAAC;YAGD,IAAI,eAAe,EAAE,CAAC;gBACrB,yBAAyB,EAAE,CAAA;gBAE3B,IAAI,mBAAmB,CAAC,MAAM,CAAC,EAAE,CAAC;oBACjC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;oBACrC,SAAQ;gBACT,CAAC;YACF,CAAC;YAED,KAAK,MAAM,IAAI,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;gBACjC,IAAI,mBAAmB,CAAC,IAAI,CAAC,EAAE,CAAC;oBAC/B,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;oBACnC,SAAQ;gBACT,CAAC;gBAED,yBAAyB,EAAE,CAAA;gBAE3B,IAAI,mBAAmB,CAAC,IAAI,CAAC,EAAE,CAAC;oBAC/B,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;oBACnC,SAAQ;gBACT,CAAC;gBAED,MAAM,IAAI,KAAK,CAAC,gCAAgC,IAAI,CAAC,MAAM,mDAAmD,iBAAiB,EAAE,CAAC,CAAA;YACnI,CAAC;QACF,CAAC;IACF,CAAC;IAED,yBAAyB,EAAE,CAAA;IAE3B,OAAO,SAAS,CAAA;AACjB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,KAAK,CAAC,IAAY,EAAE,QAAgB;IACzD,MAAM,aAAa,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAA;IACtD,MAAM,SAAS,GAAe,EAAE,CAAA;IAEhC,KAAK,MAAM,YAAY,IAAI,aAAa,EAAE,CAAC;QAC1C,MAAM,QAAQ,GAAG,IAAI,QAAQ,EAAE,CAAA;QAE/B,IAAI,aAAa,GAAG,IAAI,MAAM,EAAE,CAAA;QAChC,MAAM,SAAS,GAAG,MAAM,YAAY,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;QAE5D,KAAK,IAAI,SAAS,GAAG,CAAC,EAAE,SAAS,GAAG,SAAS,CAAC,MAAM,EAAE,SAAS,EAAE,EAAE,CAAC;YACnE,MAAM,IAAI,GAAG,IAAI,IAAI,CAAC,SAAS,CAAC,SAAS,CAAC,EAAE,SAAS,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;YAE9E,IAAI,IAAI,CAAC,iBAAiB,EAAE,CAAC;gBAC5B,MAAM,cAAc,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,gBAAgB,CAAC,CAAA;gBAChE,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,cAAc,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,mBAAmB,CAAC,CAAC,CAAA;gBACxG,QAAQ,CAAC,OAAO,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;gBAEpC,aAAa,GAAG,IAAI,MAAM,EAAE,CAAA;gBAC5B,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,cAAc,GAAG,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC,CAAA;YACnF,CAAC;iBAAM,CAAC;gBACP,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAC/B,CAAC;QACF,CAAC;QAED,IAAI,aAAa,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACpC,QAAQ,CAAC,OAAO,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;QACrC,CAAC;QAED,SAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;IACzB,CAAC;IAED,OAAO,SAAS,CAAA;AACjB,CAAC;AAED,MAAM,UAAU,gBAAgB,CAAC,IAAY,EAAE,QAAgB;IAC9D,MAAM,aAAa,GAAG,oBAAoB,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAA;IAE1D,OAAO,gBAAgB,CAAC,aAAa,CAAC,IAAI,EAAE,gBAAgB,CAAC,YAAY,CAAC,aAAa,CAAC,CAAC,CAAA;AAC1F,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY,CAAC,IAAY,EAAE,QAAgB;IAChE,MAAM,aAAa,GAAG,oBAAoB,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAA;IAE1D,IAAI,aAAa,IAAI,IAAI,IAAI,aAAa,IAAI,KAAK,EAAE,CAAC;QACrD,OAAO,6BAA6B,CAAC,IAAI,EAAE,SAAS,EAAE,IAAI,CAAC,CAAA;IAC5D,CAAC;SAAM,IAAI,aAAa,IAAI,IAAI,EAAE,CAAC;QAClC,OAAO,iCAAiC,CAAC,IAAI,CAAC,CAAA;IAC/C,CAAC;SAAM,CAAC;QACP,OAAO,gBAAgB,CAAC,SAAS,CAAC,IAAI,EAAE,gBAAgB,CAAC,YAAY,CAAC,aAAa,CAAC,CAAC,CAAA;IACtF,CAAC;AACF,CAAC;AAED,MAAM,UAAU,iBAAiB,CAAC,IAAY,EAAE,eAAmC,EAAE,UAAgC;IACpH,IAAI,UAAU,GAAa,EAAE,CAAA;IAE7B,IAAI,eAAe,IAAI,QAAQ,EAAE,CAAC;QACjC,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,WAAW,CAAC,CAAA;IACrC,CAAC;SAAM,IAAI,eAAe,IAAI,QAAQ,EAAE,CAAC;QACxC,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,kBAAkB,CAAC,CAAA;IAC5C,CAAC;SAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,iCAAiC,eAAe,EAAE,CAAC,CAAA;IACpE,CAAC;IAED,IAAI,UAAU,IAAI,kBAAkB,EAAE,CAAC;QACtC,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,CAAC,WAAW,EAAE,GAAG,CAAC,CAAC,CAAA;IACjE,CAAC;SAAM,IAAI,UAAU,IAAI,UAAU,EAAE,CAAC;QACrC,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAA;IAC5D,CAAC;IAED,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAA;IAC1C,UAAU,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IAEjD,OAAO,UAAU,CAAA;AAClB,CAAC"}
1
+ {"version":3,"file":"Segmentation.js","sourceRoot":"","sources":["../../src/nlp/Segmentation.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,gBAAgB,MAAM,mBAAmB,CAAA;AACrD,OAAO,EAAE,6BAA6B,EAAE,MAAM,0BAA0B,CAAA;AAExE,OAAO,EAAE,QAAQ,EAAE,aAAa,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AAC9F,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAA;AAC7D,OAAO,EAAE,iCAAiC,EAAE,MAAM,2BAA2B,CAAA;AAG7E,MAAM,GAAG,GAAG,WAAW,CAAA;AAEvB,MAAM,CAAC,MAAM,oBAAoB,GAAG,yBAAyB,CAAA;AAC7D,MAAM,CAAC,MAAM,kBAAkB,GAAG,oBAAoB,CAAA;AACtD,MAAM,CAAC,MAAM,gBAAgB,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAA;AAC/C,MAAM,CAAC,MAAM,kBAAkB,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAA;AACjD,MAAM,CAAC,MAAM,WAAW,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAA;AAEzI,MAAM,UAAU,kBAAkB,CAAC,GAAW;IAC7C,OAAO,MAAM,CAAC,GAAG,CAAC,IAAI,WAAW,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAA;AAChD,CAAC;AAED,MAAM,UAAU,MAAM,CAAC,GAAW;IACjC,GAAG,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;IAChB,OAAO,oBAAoB,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,WAAW,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAA;AACnE,CAAC;AAED,MAAM,UAAU,aAAa,CAAC,GAAW;IACxC,OAAO,kBAAkB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;AACpC,CAAC;AAED,MAAM,OAAO,QAAQ;IACpB,OAAO,GAAa,EAAE,CAAA;IAEb,mBAAmB,GAAG,IAAI,CAAA;IAEnC,IAAI,MAAM,KAAK,OAAO,QAAQ,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,MAAM,CAAC,CAAA,CAAC,CAAC;IAEzE,IAAI,IAAI,KAAK,OAAO,IAAI,CAAC,OAAO,CAAC,MAAM,CAAS,CAAC,MAAM,EAAE,MAAM,EAAE,EAAE,CAAC,MAAM,GAAG,MAAM,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA,CAAC,CAAC;CAC/F;AAED,MAAM,OAAO,MAAM;IAClB,KAAK,GAAW,EAAE,CAAA;IAElB,IAAI,MAAM,KAAK,OAAO,QAAQ,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA,CAAC,CAAC;IAEnE,IAAI,IAAI,KAAK,OAAO,IAAI,CAAC,KAAK,CAAC,MAAM,CAAS,CAAC,MAAM,EAAE,IAAI,EAAE,EAAE,CAAC,MAAM,GAAG,IAAI,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA,CAAC,CAAC;IAEzF,IAAI,QAAQ;QACX,IAAI,IAAI,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;YAC5B,OAAO,SAAS,CAAA;QACjB,CAAC;QAED,OAAO,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IACzC,CAAC;IAED,IAAI,mBAAmB,KAAK,OAAO,IAAI,CAAC,QAAQ,IAAI,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,mBAAmB,CAAC,CAAC,CAAC,KAAK,CAAA,CAAC,CAAC;CACtG;AAED,MAAM,OAAO,IAAI;IACP,IAAI,CAAQ;IACrB,mBAAmB,CAAS;IAE5B,YAAY,IAAY,EAAE,mBAA4B;QACrD,IAAI,CAAC,IAAI,GAAG,IAAI,CAAA;QAChB,IAAI,CAAC,mBAAmB,GAAG,mBAAmB,CAAA;IAC/C,CAAC;IAED,IAAI,uBAAuB,KAAK,OAAO,CAAC,oBAAoB,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,YAAY,CAAA,CAAC,CAAC;IAEpG,IAAI,YAAY,KAAK,OAAO,WAAW,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA,CAAC,CAAC;IAE7D,IAAI,iBAAiB,KAAK,OAAO,IAAI,CAAC,uBAAuB,IAAI,aAAa,CAAC,IAAI,CAAC,IAAI,EAAE,gBAAgB,CAAC,CAAA,CAAC,CAAC;IAE7G,IAAI,MAAM,KAAK,OAAO,IAAI,CAAC,IAAI,CAAC,MAAM,CAAA,CAAC,CAAC;CACxC;AAID,MAAM,OAAO,QAAQ;IACpB,QAAQ,GAAc,EAAE,CAAA;IAExB,IAAI,MAAM,KAAK,OAAO,QAAQ,CAAC,IAAI,CAAC,QAAQ,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,MAAM,CAAC,CAAA,CAAC,CAAC;IAE1E,IAAI,IAAI,KAAK,OAAO,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAS,CAAC,MAAM,EAAE,OAAO,EAAE,EAAE,CAAC,MAAM,GAAG,OAAO,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA,CAAC,CAAC;IAElG,IAAI,OAAO,KAAK,OAAO,IAAI,CAAC,MAAM,IAAI,CAAC,CAAA,CAAC,CAAC;IAEzC,IAAI,UAAU,KAAK,OAAO,CAAC,IAAI,CAAC,OAAO,CAAA,CAAC,CAAC;IAEzC,IAAI,WAAW;QACd,IAAI,IAAI,CAAC,OAAO,EAAE,CAAC;YAClB,OAAO,SAAS,CAAA;QACjB,CAAC;QAED,OAAO,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IAC/C,CAAC;CACD;AAED,MAAM,CAAC,KAAK,UAAU,gBAAgB,CAAC,IAAY,EAAE,iBAAyB,EAAE,QAAgB,EAAE,iBAAiB,GAAG,IAAI,EAAE,eAAe,GAAG,IAAI;IACjJ,MAAM,UAAU,GAAG,MAAM,KAAK,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAA;IAE9C,MAAM,SAAS,GAAe,EAAE,CAAA;IAChC,IAAI,eAAe,GAAG,IAAI,QAAQ,EAAE,CAAA;IAEpC,MAAM,oCAAoC,GAAG,GAAG,EAAE,CAAC,iBAAiB,GAAG,eAAe,CAAC,MAAM,CAAA;IAC7F,MAAM,yBAAyB,GAAG,GAAG,EAAE;QACtC,IAAI,eAAe,CAAC,UAAU,EAAE,CAAC;YAChC,SAAS,CAAC,IAAI,CAAC,eAAe,CAAC,CAAA;YAC/B,eAAe,GAAG,IAAI,QAAQ,EAAE,CAAA;QACjC,CAAC;IACF,CAAC,CAAA;IAED,MAAM,mBAAmB,GAAG,CAAC,OAAgB,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,IAAI,oCAAoC,EAAE,CAAA;IAE1G,KAAK,MAAM,QAAQ,IAAI,UAAU,EAAE,CAAC;QACnC,IAAI,mBAAmB,CAAC,QAAQ,CAAC,EAAE,CAAC;YACnC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;YACvC,SAAQ;QACT,CAAC;QAED,IAAI,iBAAiB,EAAE,CAAC;YACvB,yBAAyB,EAAE,CAAA;YAE3B,IAAI,mBAAmB,CAAC,QAAQ,CAAC,EAAE,CAAC;gBACnC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;gBACvC,SAAQ;YACT,CAAC;QACF,CAAC;QAED,KAAK,MAAM,MAAM,IAAI,QAAQ,CAAC,OAAO,EAAE,CAAC;YACvC,IAAI,mBAAmB,CAAC,MAAM,CAAC,EAAE,CAAC;gBACjC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;gBACrC,SAAQ;YACT,CAAC;YAGD,IAAI,eAAe,EAAE,CAAC;gBACrB,yBAAyB,EAAE,CAAA;gBAE3B,IAAI,mBAAmB,CAAC,MAAM,CAAC,EAAE,CAAC;oBACjC,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;oBACrC,SAAQ;gBACT,CAAC;YACF,CAAC;YAED,KAAK,MAAM,IAAI,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;gBACjC,IAAI,mBAAmB,CAAC,IAAI,CAAC,EAAE,CAAC;oBAC/B,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;oBACnC,SAAQ;gBACT,CAAC;gBAED,yBAAyB,EAAE,CAAA;gBAE3B,IAAI,mBAAmB,CAAC,IAAI,CAAC,EAAE,CAAC;oBAC/B,eAAe,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;oBACnC,SAAQ;gBACT,CAAC;gBAED,MAAM,IAAI,KAAK,CAAC,gCAAgC,IAAI,CAAC,MAAM,mDAAmD,iBAAiB,EAAE,CAAC,CAAA;YACnI,CAAC;QACF,CAAC;IACF,CAAC;IAED,yBAAyB,EAAE,CAAA;IAE3B,OAAO,SAAS,CAAA;AACjB,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,KAAK,CAAC,IAAY,EAAE,QAAgB;IACzD,MAAM,aAAa,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAA;IACtD,MAAM,SAAS,GAAe,EAAE,CAAA;IAEhC,KAAK,MAAM,YAAY,IAAI,aAAa,EAAE,CAAC;QAC1C,MAAM,QAAQ,GAAG,IAAI,QAAQ,EAAE,CAAA;QAE/B,IAAI,aAAa,GAAG,IAAI,MAAM,EAAE,CAAA;QAChC,MAAM,SAAS,GAAG,MAAM,YAAY,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;QAE5D,KAAK,IAAI,SAAS,GAAG,CAAC,EAAE,SAAS,GAAG,SAAS,CAAC,MAAM,EAAE,SAAS,EAAE,EAAE,CAAC;YACnE,MAAM,IAAI,GAAG,IAAI,IAAI,CAAC,SAAS,CAAC,SAAS,CAAC,EAAE,SAAS,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;YAE9E,IAAI,IAAI,CAAC,iBAAiB,EAAE,CAAC;gBAC5B,MAAM,cAAc,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,gBAAgB,CAAC,CAAA;gBAChE,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,cAAc,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,mBAAmB,CAAC,CAAC,CAAA;gBACxG,QAAQ,CAAC,OAAO,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;gBAEpC,aAAa,GAAG,IAAI,MAAM,EAAE,CAAA;gBAC5B,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,cAAc,GAAG,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC,CAAA;YACnF,CAAC;iBAAM,CAAC;gBACP,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAC/B,CAAC;QACF,CAAC;QAED,IAAI,aAAa,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACpC,QAAQ,CAAC,OAAO,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;QACrC,CAAC;QAED,SAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;IACzB,CAAC;IAED,OAAO,SAAS,CAAA;AACjB,CAAC;AAED,MAAM,UAAU,gBAAgB,CAAC,IAAY,EAAE,QAAgB;IAC9D,MAAM,aAAa,GAAG,oBAAoB,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAA;IAE1D,OAAO,gBAAgB,CAAC,aAAa,CAAC,IAAI,EAAE,gBAAgB,CAAC,YAAY,CAAC,aAAa,CAAC,CAAC,CAAA;AAC1F,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY,CAAC,IAAY,EAAE,QAAgB;IAChE,MAAM,aAAa,GAAG,oBAAoB,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAA;IAE1D,IAAI,aAAa,IAAI,IAAI,IAAI,aAAa,IAAI,KAAK,EAAE,CAAC;QACrD,OAAO,6BAA6B,CAAC,IAAI,EAAE,SAAS,EAAE,IAAI,CAAC,CAAA;IAC5D,CAAC;SAAM,IAAI,aAAa,IAAI,IAAI,EAAE,CAAC;QAClC,OAAO,iCAAiC,CAAC,IAAI,CAAC,CAAA;IAC/C,CAAC;SAAM,CAAC;QACP,OAAO,gBAAgB,CAAC,SAAS,CAAC,IAAI,EAAE,gBAAgB,CAAC,YAAY,CAAC,aAAa,CAAC,CAAC,CAAA;IACtF,CAAC;AACF,CAAC;AAED,MAAM,UAAU,iBAAiB,CAAC,IAAY,EAAE,eAAmC,EAAE,UAAgC;IACpH,IAAI,UAAU,GAAa,EAAE,CAAA;IAE7B,IAAI,eAAe,IAAI,QAAQ,EAAE,CAAC;QACjC,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,WAAW,CAAC,CAAA;IACrC,CAAC;SAAM,IAAI,eAAe,IAAI,QAAQ,EAAE,CAAC;QACxC,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,kBAAkB,CAAC,CAAA;IAC5C,CAAC;SAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,iCAAiC,eAAe,EAAE,CAAC,CAAA;IACpE,CAAC;IAED,IAAI,UAAU,IAAI,kBAAkB,EAAE,CAAC;QACtC,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,CAAC,WAAW,EAAE,GAAG,CAAC,CAAC,CAAA;IACjE,CAAC;SAAM,IAAI,UAAU,IAAI,UAAU,EAAE,CAAC;QACrC,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAA;IAC5D,CAAC;IAED,UAAU,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAA;IAC1C,UAAU,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IAEjD,OAAO,UAAU,CAAA;AAClB,CAAC;AAED,MAAM,UAAU,YAAY,CAAC,IAAY;IACxC,OAAO,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAA;AAC5B,CAAC"}
@@ -1,7 +1,7 @@
1
- import { getShortLanguageCode } from "../utilities/Locale.js";
1
+ import { getShortLanguageCode } from '../utilities/Locale.js';
2
2
  export function getNormalizedFragmentsForSpeech(words, language) {
3
3
  language = getShortLanguageCode(language);
4
- if (language != "en") {
4
+ if (language != 'en') {
5
5
  return { normalizedFragments: [...words], referenceFragments: [...words] };
6
6
  }
7
7
  const numberPattern = /^[0-9][0-9\,\.]*$/;
@@ -9,22 +9,22 @@ export function getNormalizedFragmentsForSpeech(words, language) {
9
9
  const fourDigitDecadePattern = /^[0-9][0-9][0-9]0s$/;
10
10
  const fourDigitYearRangePattern = /^[0-9][0-9][0-9][0-9][\-\–][0-9][0-9][0-9][0-9]$/;
11
11
  const wordsPrecedingAYear = [
12
- "in", "the", "a", "to", "of", "since", "from", "between", "by", "until", "around", "before", "after",
13
- "his", "her", "year", "years", "during", "copyright", "©", "early", "mid", "late",
14
- "january", "february", "march", "april", "may", "june", "july", "august", "september", "october", "november", "december",
15
- "jan", "feb", "mar", "apr", "may", "jun", "jul", "aug", "sep", "oct", "nov", "dec"
12
+ 'in', 'the', 'a', 'to', 'of', 'since', 'from', 'between', 'by', 'until', 'around', 'before', 'after',
13
+ 'his', 'her', 'year', 'years', 'during', 'copyright', '©', 'early', 'mid', 'late',
14
+ 'january', 'february', 'march', 'april', 'may', 'june', 'july', 'august', 'september', 'october', 'november', 'december',
15
+ 'jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec'
16
16
  ];
17
17
  const wordsPrecedingADecade = [
18
- "the", "in", "early", "mid", "late", "a"
18
+ 'the', 'in', 'early', 'mid', 'late', 'a'
19
19
  ];
20
20
  const symbolsPrecedingACurrency = [
21
- "$", "€", "£", "¥"
21
+ '$', '€', '£', '¥'
22
22
  ];
23
23
  const symbolsPrecedingACurrencyAsWords = [
24
- "dollars", "euros", "pounds", "yen"
24
+ 'dollars', 'euros', 'pounds', 'yen'
25
25
  ];
26
26
  const wordsSucceedingACurrency = [
27
- "million", "billion", "trillion"
27
+ 'million', 'billion', 'trillion'
28
28
  ];
29
29
  const normalizedFragments = [];
30
30
  const referenceFragments = [];
@@ -33,7 +33,7 @@ export function getNormalizedFragmentsForSpeech(words, language) {
33
33
  const lowerCaseWord = word.toLowerCase();
34
34
  const nextWords = words.slice(wordIndex + 1);
35
35
  const nextWord = nextWords[0];
36
- if ( // Normalize a four digit year pattern, e.g. "in 1995".
36
+ if ( // Normalize a four digit year pattern, e.g. 'in 1995'.
37
37
  wordsPrecedingAYear.includes(lowerCaseWord) &&
38
38
  fourDigitYearPattern.test(nextWord)) {
39
39
  const normalizedString = normalizeFourDigitYearString(nextWord);
@@ -43,7 +43,7 @@ export function getNormalizedFragmentsForSpeech(words, language) {
43
43
  referenceFragments.push(nextWord);
44
44
  wordIndex += 1;
45
45
  }
46
- else if ( // Normalize a four digit decade pattern, e.g. "the 1980s".
46
+ else if ( // Normalize a four digit decade pattern, e.g. 'the 1980s'.
47
47
  wordsPrecedingADecade.includes(lowerCaseWord) &&
48
48
  fourDigitDecadePattern.test(nextWord)) {
49
49
  const normalizedString = normalizeFourDigitDecadeString(nextWord);
@@ -53,17 +53,17 @@ export function getNormalizedFragmentsForSpeech(words, language) {
53
53
  referenceFragments.push(nextWord);
54
54
  wordIndex += 1;
55
55
  }
56
- else if ( // Normalize a year range pattern, e.g. "1835-1896"
57
- fourDigitYearRangePattern.test(words.slice(wordIndex, wordIndex + 3).join(""))) {
56
+ else if ( // Normalize a year range pattern, e.g. '1835-1896'
57
+ fourDigitYearRangePattern.test(words.slice(wordIndex, wordIndex + 3).join(''))) {
58
58
  normalizedFragments.push(normalizeFourDigitYearString(words[wordIndex]));
59
59
  referenceFragments.push(words[wordIndex]);
60
- normalizedFragments.push("to");
60
+ normalizedFragments.push('to');
61
61
  referenceFragments.push(words[wordIndex + 1]);
62
62
  normalizedFragments.push(normalizeFourDigitYearString(words[wordIndex + 2]));
63
63
  referenceFragments.push(words[wordIndex + 2]);
64
64
  wordIndex += 2;
65
65
  }
66
- else if ( // Normalize a currency pattern, e.g. "$53.1 million", "€3.53"
66
+ else if ( // Normalize a currency pattern, e.g. '$53.1 million', '€3.53'
67
67
  symbolsPrecedingACurrency.includes(lowerCaseWord) &&
68
68
  numberPattern.test(nextWord)) {
69
69
  let currencyWord = symbolsPrecedingACurrencyAsWords[symbolsPrecedingACurrency.indexOf(lowerCaseWord)];
@@ -1,5 +1,5 @@
1
- import { Timeline } from "../utilities/Timeline.js";
2
- import { RawAudio } from "../audio/AudioUtilities.js";
1
+ import { Timeline } from '../utilities/Timeline.js';
2
+ import { RawAudio } from '../audio/AudioUtilities.js';
3
3
  export declare function recgonize(rawAudio: RawAudio, languageCode: string, region: string, accessKeyId: string, secretAccessKey: string): Promise<{
4
4
  transcript: string;
5
5
  timeline: Timeline;
@@ -1,11 +1,11 @@
1
- import { wordCharacterPattern } from "../nlp/Segmentation.js";
2
- import * as FFMpegTranscoder from "../codecs/FFMpegTranscoder.js";
3
- import { Logger } from "../utilities/Logger.js";
1
+ import { wordCharacterPattern } from '../nlp/Segmentation.js';
2
+ import * as FFMpegTranscoder from '../codecs/FFMpegTranscoder.js';
3
+ import { Logger } from '../utilities/Logger.js';
4
4
  export async function recgonize(rawAudio, languageCode, region, accessKeyId, secretAccessKey) {
5
- const flac16Khz16bitMonoAudio = await FFMpegTranscoder.encodeFromChannels(rawAudio, { format: "flac", sampleRate: 16000, sampleFormat: "s16", channelCount: 1 });
5
+ const flac16Khz16bitMonoAudio = await FFMpegTranscoder.encodeFromChannels(rawAudio, { format: 'flac', sampleRate: 16000, sampleFormat: 's16', channelCount: 1 });
6
6
  const logger = new Logger();
7
- logger.start("Initialize Amazon Transcribe streaming client module");
8
- const streamingTranscribeSdk = await import("@aws-sdk/client-transcribe-streaming");
7
+ logger.start('Initialize Amazon Transcribe streaming client module');
8
+ const streamingTranscribeSdk = await import('@aws-sdk/client-transcribe-streaming');
9
9
  const streamingTranscribeClient = new streamingTranscribeSdk.TranscribeStreamingClient({
10
10
  region,
11
11
  credentials: {
@@ -15,7 +15,6 @@ export async function recgonize(rawAudio, languageCode, region, accessKeyId, sec
15
15
  });
16
16
  const audioStream = async function* () {
17
17
  const chunkSize = 2 ** 12;
18
- //const audioSamples = encodeToAudioBuffer(rawAudio.audioChannels, 16, SampleFormat.PCM)
19
18
  for (let i = 0; i < flac16Khz16bitMonoAudio.length; i += chunkSize) {
20
19
  const chunk = flac16Khz16bitMonoAudio.subarray(i, i + chunkSize);
21
20
  yield { AudioEvent: { AudioChunk: chunk } };
@@ -24,13 +23,13 @@ export async function recgonize(rawAudio, languageCode, region, accessKeyId, sec
24
23
  const params = {
25
24
  LanguageCode: languageCode,
26
25
  MediaSampleRateHertz: rawAudio.sampleRate,
27
- MediaEncoding: "flac",
26
+ MediaEncoding: 'flac',
28
27
  AudioStream: audioStream(),
29
28
  };
30
- logger.start("Request recognition from Amazon Transcribe..");
29
+ logger.start('Request recognition from Amazon Transcribe');
31
30
  const command = new streamingTranscribeSdk.StartStreamTranscriptionCommand(params);
32
31
  const response = await streamingTranscribeClient.send(command);
33
- let transcript = "";
32
+ let transcript = '';
34
33
  let events = [];
35
34
  for await (const event of response.TranscriptResultStream) {
36
35
  if (!event.TranscriptEvent) {
@@ -50,11 +49,11 @@ export async function recgonize(rawAudio, languageCode, region, accessKeyId, sec
50
49
  //logger.log(firstAlternative.Transcript!)
51
50
  if (firstResult.IsPartial === false) {
52
51
  events = [...events, ...firstAlternative.Items];
53
- transcript += " " + firstAlternative.Transcript;
52
+ transcript += ' ' + firstAlternative.Transcript;
54
53
  }
55
54
  }
56
- logger.start("Process result");
57
- transcript = transcript.replace(/ +/g, " ").trim();
55
+ logger.start('Process result');
56
+ transcript = transcript.replace(/ +/g, ' ').trim();
58
57
  const timeline = [];
59
58
  for (const event of events) {
60
59
  const text = event.Content;
@@ -66,7 +65,7 @@ export async function recgonize(rawAudio, languageCode, region, accessKeyId, sec
66
65
  const confidence = event.Confidence;
67
66
  timeline[timeline.length - 1].endTime = startTime;
68
67
  timeline.push({
69
- type: "word",
68
+ type: 'word',
70
69
  text,
71
70
  startTime,
72
71
  endTime,
@@ -1 +1 @@
1
- {"version":3,"file":"AmazonTranscribeSTT.js","sourceRoot":"","sources":["../../src/recognition/AmazonTranscribeSTT.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAA;AAC7D,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAI/C,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,YAAoB,EAAE,MAAc,EAAE,WAAmB,EAAE,eAAuB;IACrI,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,sDAAsD,CAAC,CAAA;IAEpE,MAAM,sBAAsB,GAAG,MAAM,MAAM,CAAC,sCAAsC,CAAC,CAAA;IAEnF,MAAM,yBAAyB,GAAG,IAAI,sBAAsB,CAAC,yBAAyB,CAAC;QACtF,MAAM;QACN,WAAW,EAAE;YACZ,WAAW;YACX,eAAe;SACf;KACD,CAAC,CAAA;IAEF,MAAM,WAAW,GAAG,KAAK,SAAS,CAAC;QAClC,MAAM,SAAS,GAAG,CAAC,IAAI,EAAE,CAAA;QACzB,wFAAwF;QAExF,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,uBAAuB,CAAC,MAAM,EAAE,CAAC,IAAI,SAAS,EAAE,CAAC;YACpE,MAAM,KAAK,GAAG,uBAAuB,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,GAAG,SAAS,CAAC,CAAA;YAEhE,MAAM,EAAE,UAAU,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,EAAE,CAAA;QAC5C,CAAC;IACF,CAAC,CAAA;IAED,MAAM,MAAM,GAAyC;QACpD,YAAY,EAAE,YAA4B;QAC1C,oBAAoB,EAAE,QAAQ,CAAC,UAAU;QACzC,aAAa,EAAE,MAAM;QACrB,WAAW,EAAE,WAAW,EAAE;KAC1B,CAAA;IAED,MAAM,CAAC,KAAK,CAAC,8CAA8C,CAAC,CAAA;IAE5D,MAAM,OAAO,GAAG,IAAI,sBAAsB,CAAC,+BAA+B,CAAC,MAAM,CAAC,CAAA;IAElF,MAAM,QAAQ,GAAG,MAAM,yBAAyB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IAE9D,IAAI,UAAU,GAAG,EAAE,CAAA;IACnB,IAAI,MAAM,GAAW,EAAE,CAAA;IAEvB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,QAAQ,CAAC,sBAAuB,EAAE,CAAC;QAC5D,IAAI,CAAC,KAAK,CAAC,eAAe,EAAE,CAAC;YAC5B,SAAQ;QACT,CAAC;QAED,MAAM,eAAe,GAAG,KAAK,CAAC,eAAe,CAAA;QAE7C,MAAM,OAAO,GAAG,eAAe,CAAC,UAAW,CAAC,OAAQ,CAAA;QAEpD,IAAI,OAAO,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;YACzB,SAAQ;QACT,CAAC;QAED,MAAM,WAAW,GAAG,OAAO,CAAC,CAAC,CAAC,CAAA;QAC9B,MAAM,YAAY,GAAG,WAAW,CAAC,YAAY,CAAA;QAE7C,IAAI,CAAC,YAAY,IAAI,YAAY,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;YAC/C,SAAQ;QACT,CAAC;QAED,MAAM,gBAAgB,GAAG,YAAY,CAAC,CAAC,CAAC,CAAA;QACxC,0CAA0C;QAE1C,IAAI,WAAW,CAAC,SAAS,KAAK,KAAK,EAAE,CAAC;YACrC,MAAM,GAAG,CAAC,GAAG,MAAM,EAAE,GAAG,gBAAgB,CAAC,KAAM,CAAC,CAAA;YAChD,UAAU,IAAI,GAAG,GAAG,gBAAgB,CAAC,UAAW,CAAA;QACjD,CAAC;IACF,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,gBAAgB,CAAC,CAAA;IAE9B,UAAU,GAAG,UAAU,CAAC,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAElD,MAAM,QAAQ,GAAa,EAAE,CAAA;IAE7B,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC5B,MAAM,IAAI,GAAG,KAAK,CAAC,OAAQ,CAAA;QAE3B,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YACtC,SAAQ;QACT,CAAC;QAED,MAAM,SAAS,GAAG,KAAK,CAAC,SAAU,CAAA;QAClC,MAAM,OAAO,GAAG,KAAK,CAAC,OAAQ,CAAA;QAC9B,MAAM,UAAU,GAAG,KAAK,CAAC,UAAU,CAAA;QAEnC,QAAQ,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,OAAO,GAAG,SAAS,CAAA;QAEjD,QAAQ,CAAC,IAAI,CACZ;YACC,IAAI,EAAE,MAAM;YACZ,IAAI;YACJ,SAAS;YACT,OAAO;YACP,UAAU;SACV,CAAC,CAAA;IACJ,CAAC;IAED,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;AAChC,CAAC"}
1
+ {"version":3,"file":"AmazonTranscribeSTT.js","sourceRoot":"","sources":["../../src/recognition/AmazonTranscribeSTT.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,oBAAoB,EAAE,MAAM,wBAAwB,CAAA;AAC7D,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAI/C,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,YAAoB,EAAE,MAAc,EAAE,WAAmB,EAAE,eAAuB;IACrI,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,sDAAsD,CAAC,CAAA;IAEpE,MAAM,sBAAsB,GAAG,MAAM,MAAM,CAAC,sCAAsC,CAAC,CAAA;IAEnF,MAAM,yBAAyB,GAAG,IAAI,sBAAsB,CAAC,yBAAyB,CAAC;QACtF,MAAM;QACN,WAAW,EAAE;YACZ,WAAW;YACX,eAAe;SACf;KACD,CAAC,CAAA;IAEF,MAAM,WAAW,GAAG,KAAK,SAAS,CAAC;QAClC,MAAM,SAAS,GAAG,CAAC,IAAI,EAAE,CAAA;QAEzB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,uBAAuB,CAAC,MAAM,EAAE,CAAC,IAAI,SAAS,EAAE,CAAC;YACpE,MAAM,KAAK,GAAG,uBAAuB,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC,GAAG,SAAS,CAAC,CAAA;YAEhE,MAAM,EAAE,UAAU,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,EAAE,CAAA;QAC5C,CAAC;IACF,CAAC,CAAA;IAED,MAAM,MAAM,GAAyC;QACpD,YAAY,EAAE,YAA4B;QAC1C,oBAAoB,EAAE,QAAQ,CAAC,UAAU;QACzC,aAAa,EAAE,MAAM;QACrB,WAAW,EAAE,WAAW,EAAE;KAC1B,CAAA;IAED,MAAM,CAAC,KAAK,CAAC,4CAA4C,CAAC,CAAA;IAE1D,MAAM,OAAO,GAAG,IAAI,sBAAsB,CAAC,+BAA+B,CAAC,MAAM,CAAC,CAAA;IAElF,MAAM,QAAQ,GAAG,MAAM,yBAAyB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IAE9D,IAAI,UAAU,GAAG,EAAE,CAAA;IACnB,IAAI,MAAM,GAAW,EAAE,CAAA;IAEvB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,QAAQ,CAAC,sBAAuB,EAAE,CAAC;QAC5D,IAAI,CAAC,KAAK,CAAC,eAAe,EAAE,CAAC;YAC5B,SAAQ;QACT,CAAC;QAED,MAAM,eAAe,GAAG,KAAK,CAAC,eAAe,CAAA;QAE7C,MAAM,OAAO,GAAG,eAAe,CAAC,UAAW,CAAC,OAAQ,CAAA;QAEpD,IAAI,OAAO,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;YACzB,SAAQ;QACT,CAAC;QAED,MAAM,WAAW,GAAG,OAAO,CAAC,CAAC,CAAC,CAAA;QAC9B,MAAM,YAAY,GAAG,WAAW,CAAC,YAAY,CAAA;QAE7C,IAAI,CAAC,YAAY,IAAI,YAAY,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;YAC/C,SAAQ;QACT,CAAC;QAED,MAAM,gBAAgB,GAAG,YAAY,CAAC,CAAC,CAAC,CAAA;QACxC,0CAA0C;QAE1C,IAAI,WAAW,CAAC,SAAS,KAAK,KAAK,EAAE,CAAC;YACrC,MAAM,GAAG,CAAC,GAAG,MAAM,EAAE,GAAG,gBAAgB,CAAC,KAAM,CAAC,CAAA;YAChD,UAAU,IAAI,GAAG,GAAG,gBAAgB,CAAC,UAAW,CAAA;QACjD,CAAC;IACF,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,gBAAgB,CAAC,CAAA;IAE9B,UAAU,GAAG,UAAU,CAAC,OAAO,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAElD,MAAM,QAAQ,GAAa,EAAE,CAAA;IAE7B,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC5B,MAAM,IAAI,GAAG,KAAK,CAAC,OAAQ,CAAA;QAE3B,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YACtC,SAAQ;QACT,CAAC;QAED,MAAM,SAAS,GAAG,KAAK,CAAC,SAAU,CAAA;QAClC,MAAM,OAAO,GAAG,KAAK,CAAC,OAAQ,CAAA;QAC9B,MAAM,UAAU,GAAG,KAAK,CAAC,UAAU,CAAA;QAEnC,QAAQ,CAAC,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,OAAO,GAAG,SAAS,CAAA;QAEjD,QAAQ,CAAC,IAAI,CACZ;YACC,IAAI,EAAE,MAAM;YACZ,IAAI;YACJ,SAAS;YACT,OAAO;YACP,UAAU;SACV,CAAC,CAAA;IACJ,CAAC;IAED,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;AAChC,CAAC"}
@@ -1,11 +1,11 @@
1
1
  import * as SpeechSDK from 'microsoft-cognitiveservices-speech-sdk';
2
- import { encodeWaveBuffer } from '../audio/AudioUtilities.js';
2
+ import { encodeRawAudioToWave } from '../audio/AudioUtilities.js';
3
3
  import { Logger } from '../utilities/Logger.js';
4
4
  export async function recognize(rawAudio, subscriptionKey, serviceRegion, languageCode, profanity = SpeechSDK.ProfanityOption.Raw) {
5
5
  const logger = new Logger();
6
- logger.start("Request recognition from Azure Cognitive Services");
6
+ logger.start('Request recognition from Azure Cognitive Services');
7
7
  const result = await requestRecognition(rawAudio, subscriptionKey, serviceRegion, languageCode);
8
- logger.start("Process result");
8
+ logger.start('Process result');
9
9
  const transcript = result.text;
10
10
  const resultObject = JSON.parse(result.json);
11
11
  const bestResult = resultObject.NBest[0];
@@ -15,7 +15,7 @@ export async function recognize(rawAudio, subscriptionKey, serviceRegion, langua
15
15
  const startTime = wordEntry.Offset / 10000000;
16
16
  const endTime = (wordEntry.Offset + wordEntry.Duration) / 10000000;
17
17
  timeline.push({
18
- type: "word",
18
+ type: 'word',
19
19
  text,
20
20
  startTime,
21
21
  endTime
@@ -25,8 +25,7 @@ export async function recognize(rawAudio, subscriptionKey, serviceRegion, langua
25
25
  return { transcript, timeline };
26
26
  }
27
27
  async function requestRecognition(rawAudio, subscriptionKey, serviceRegion, languageCode, profanity = SpeechSDK.ProfanityOption.Raw) {
28
- //const encodedAudio = await FFMpegTranscoder.encodeFromChannels(rawAudio, { format: "wav", sampleRate: 16000, sampleFormat: "s16", channelCount: 1 });
29
- const encodedAudio = encodeWaveBuffer(rawAudio);
28
+ const encodedAudio = encodeRawAudioToWave(rawAudio);
30
29
  return new Promise((resolve, reject) => {
31
30
  const audioFormat = SpeechSDK.AudioStreamFormat.getWaveFormat(16000, 16, 1, SpeechSDK.AudioFormatTag.PCM);
32
31
  const inputStream = SpeechSDK.AudioInputStream.createPushStream(audioFormat);
@@ -1 +1 @@
1
- {"version":3,"file":"AzureCognitiveServicesSTT.js","sourceRoot":"","sources":["../../src/recognition/AzureCognitiveServicesSTT.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,SAAS,MAAM,wCAAwC,CAAA;AAEnE,OAAO,EAAY,gBAAgB,EAAE,MAAM,4BAA4B,CAAA;AACvE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAG/C,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,eAAuB,EAAE,aAAqB,EAAE,YAAoB,EAAE,YAAuC,SAAS,CAAC,eAAe,CAAC,GAAG;IAC7L,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAC3B,MAAM,CAAC,KAAK,CAAC,mDAAmD,CAAC,CAAA;IAEjE,MAAM,MAAM,GAAG,MAAM,kBAAkB,CAAC,QAAQ,EAAE,eAAe,EAAE,aAAa,EAAE,YAAY,CAAC,CAAA;IAE/F,MAAM,CAAC,KAAK,CAAC,gBAAgB,CAAC,CAAA;IAE9B,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAA;IAE9B,MAAM,YAAY,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;IAC5C,MAAM,UAAU,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;IAExC,MAAM,QAAQ,GAAa,EAAE,CAAA;IAE7B,KAAK,MAAM,SAAS,IAAI,UAAU,CAAC,KAAK,EAAE,CAAC;QAC1C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,CAAA;QAC3B,MAAM,SAAS,GAAG,SAAS,CAAC,MAAM,GAAG,QAAQ,CAAA;QAC7C,MAAM,OAAO,GAAG,CAAC,SAAS,CAAC,MAAM,GAAG,SAAS,CAAC,QAAQ,CAAC,GAAG,QAAQ,CAAA;QAElE,QAAQ,CAAC,IAAI,CAAC;YACb,IAAI,EAAE,MAAM;YACZ,IAAI;YACJ,SAAS;YACT,OAAO;SACP,CAAC,CAAA;IACH,CAAC;IAED,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;AAChC,CAAC;AAED,KAAK,UAAU,kBAAkB,CAAC,QAAkB,EAAE,eAAuB,EAAE,aAAqB,EAAE,YAAoB,EAAE,YAAuC,SAAS,CAAC,eAAe,CAAC,GAAG;IAC/L,uJAAuJ;IACvJ,MAAM,YAAY,GAAG,gBAAgB,CAAC,QAAQ,CAAC,CAAA;IAE/C,OAAO,IAAI,OAAO,CAAoC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACzE,MAAM,WAAW,GAAG,SAAS,CAAC,iBAAiB,CAAC,aAAa,CAAC,KAAK,EAAE,EAAE,EAAE,CAAC,EAAE,SAAS,CAAC,cAAc,CAAC,GAAG,CAAC,CAAA;QAEzG,MAAM,WAAW,GAAG,SAAS,CAAC,gBAAgB,CAAC,gBAAgB,CAAC,WAAW,CAAC,CAAA;QAE5E,WAAW,CAAC,KAAK,CAAC,YAAY,CAAC,CAAA;QAC/B,WAAW,CAAC,KAAK,EAAE,CAAA;QAEnB,MAAM,WAAW,GAAG,SAAS,CAAC,WAAW,CAAC,eAAe,CAAC,WAAW,CAAC,CAAA;QAEtE,MAAM,YAAY,GAAG,SAAS,CAAC,YAAY,CAAC,gBAAgB,CAAC,eAAe,EAAE,aAAa,CAAC,CAAA;QAE5F,YAAY,CAAC,yBAAyB,GAAG,YAAY,CAAA;QAErD,YAAY,CAAC,YAAY,CAAC,SAAS,CAAC,CAAA;QACpC,YAAY,CAAC,0BAA0B,EAAE,CAAA;QAEzC,YAAY,CAAC,YAAY,GAAG,SAAS,CAAC,YAAY,CAAC,QAAQ,CAAA;QAE3D,MAAM,UAAU,GAAG,IAAI,SAAS,CAAC,gBAAgB,CAAC,YAAY,EAAE,WAAW,CAAC,CAAA;QAE5E,UAAU,CAAC,kBAAkB,CAC5B,CAAC,MAAM,EAAE,EAAE;YACV,UAAU,CAAC,KAAK,EAAE,CAAA;YAClB,OAAO,CAAC,MAAM,CAAC,CAAA;QAChB,CAAC,EAED,CAAC,KAAK,EAAE,EAAE;YACT,UAAU,CAAC,KAAK,EAAE,CAAA;YAClB,MAAM,CAAC,KAAK,CAAC,CAAA;QACd,CAAC,CAAC,CAAA;IACJ,CAAC,CAAC,CAAA;AACH,CAAC"}
1
+ {"version":3,"file":"AzureCognitiveServicesSTT.js","sourceRoot":"","sources":["../../src/recognition/AzureCognitiveServicesSTT.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,SAAS,MAAM,wCAAwC,CAAA;AAEnE,OAAO,EAAY,oBAAoB,EAAE,MAAM,4BAA4B,CAAA;AAC3E,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAG/C,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,eAAuB,EAAE,aAAqB,EAAE,YAAoB,EAAE,YAAuC,SAAS,CAAC,eAAe,CAAC,GAAG;IAC7L,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAE3B,MAAM,CAAC,KAAK,CAAC,mDAAmD,CAAC,CAAA;IAEjE,MAAM,MAAM,GAAG,MAAM,kBAAkB,CAAC,QAAQ,EAAE,eAAe,EAAE,aAAa,EAAE,YAAY,CAAC,CAAA;IAE/F,MAAM,CAAC,KAAK,CAAC,gBAAgB,CAAC,CAAA;IAE9B,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAA;IAE9B,MAAM,YAAY,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;IAC5C,MAAM,UAAU,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;IAExC,MAAM,QAAQ,GAAa,EAAE,CAAA;IAE7B,KAAK,MAAM,SAAS,IAAI,UAAU,CAAC,KAAK,EAAE,CAAC;QAC1C,MAAM,IAAI,GAAG,SAAS,CAAC,IAAI,CAAA;QAC3B,MAAM,SAAS,GAAG,SAAS,CAAC,MAAM,GAAG,QAAQ,CAAA;QAC7C,MAAM,OAAO,GAAG,CAAC,SAAS,CAAC,MAAM,GAAG,SAAS,CAAC,QAAQ,CAAC,GAAG,QAAQ,CAAA;QAElE,QAAQ,CAAC,IAAI,CAAC;YACb,IAAI,EAAE,MAAM;YACZ,IAAI;YACJ,SAAS;YACT,OAAO;SACP,CAAC,CAAA;IACH,CAAC;IAED,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;AAChC,CAAC;AAED,KAAK,UAAU,kBAAkB,CAAC,QAAkB,EAAE,eAAuB,EAAE,aAAqB,EAAE,YAAoB,EAAE,YAAuC,SAAS,CAAC,eAAe,CAAC,GAAG;IAC/L,MAAM,YAAY,GAAG,oBAAoB,CAAC,QAAQ,CAAC,CAAA;IAEnD,OAAO,IAAI,OAAO,CAAoC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACzE,MAAM,WAAW,GAAG,SAAS,CAAC,iBAAiB,CAAC,aAAa,CAAC,KAAK,EAAE,EAAE,EAAE,CAAC,EAAE,SAAS,CAAC,cAAc,CAAC,GAAG,CAAC,CAAA;QAEzG,MAAM,WAAW,GAAG,SAAS,CAAC,gBAAgB,CAAC,gBAAgB,CAAC,WAAW,CAAC,CAAA;QAE5E,WAAW,CAAC,KAAK,CAAC,YAAY,CAAC,CAAA;QAC/B,WAAW,CAAC,KAAK,EAAE,CAAA;QAEnB,MAAM,WAAW,GAAG,SAAS,CAAC,WAAW,CAAC,eAAe,CAAC,WAAW,CAAC,CAAA;QAEtE,MAAM,YAAY,GAAG,SAAS,CAAC,YAAY,CAAC,gBAAgB,CAAC,eAAe,EAAE,aAAa,CAAC,CAAA;QAE5F,YAAY,CAAC,yBAAyB,GAAG,YAAY,CAAA;QAErD,YAAY,CAAC,YAAY,CAAC,SAAS,CAAC,CAAA;QACpC,YAAY,CAAC,0BAA0B,EAAE,CAAA;QAEzC,YAAY,CAAC,YAAY,GAAG,SAAS,CAAC,YAAY,CAAC,QAAQ,CAAA;QAE3D,MAAM,UAAU,GAAG,IAAI,SAAS,CAAC,gBAAgB,CAAC,YAAY,EAAE,WAAW,CAAC,CAAA;QAE5E,UAAU,CAAC,kBAAkB,CAC5B,CAAC,MAAM,EAAE,EAAE;YACV,UAAU,CAAC,KAAK,EAAE,CAAA;YAElB,OAAO,CAAC,MAAM,CAAC,CAAA;QAChB,CAAC,EAED,CAAC,KAAK,EAAE,EAAE;YACT,UAAU,CAAC,KAAK,EAAE,CAAA;YAElB,MAAM,CAAC,KAAK,CAAC,CAAA;QACd,CAAC,CAAC,CAAA;IACJ,CAAC,CAAC,CAAA;AACH,CAAC"}
@@ -1,6 +1,6 @@
1
- import { Timeline } from "../utilities/Timeline.js";
2
- import { RawAudio } from "../audio/AudioUtilities.js";
3
- export type AudioEncoding = "LINEAR16" | "FLAC" | "MULAW" | "AMR" | "AMR" | "AMR_WB" | "OGG_OPUS" | "SPEEX_WITH_HEADER_BYTE" | "MP3" | "WEBM_OPUS";
1
+ import { Timeline } from '../utilities/Timeline.js';
2
+ import { RawAudio } from '../audio/AudioUtilities.js';
3
+ export type AudioEncoding = 'LINEAR16' | 'FLAC' | 'MULAW' | 'AMR' | 'AMR' | 'AMR_WB' | 'OGG_OPUS' | 'SPEEX_WITH_HEADER_BYTE' | 'MP3' | 'WEBM_OPUS';
4
4
  export declare function recognize(rawAudio: RawAudio, apiKey: string, languageCode?: string): Promise<{
5
5
  transcript: string;
6
6
  timeline: Timeline;
@@ -1,13 +1,13 @@
1
- import { request } from "gaxios";
2
- import * as FFMpegTranscoder from "../codecs/FFMpegTranscoder.js";
3
- import { Logger } from "../utilities/Logger.js";
4
- export async function recognize(rawAudio, apiKey, languageCode = "en-US") {
5
- const flac16Khz16bitMonoAudio = await FFMpegTranscoder.encodeFromChannels(rawAudio, { format: "flac", sampleRate: 16000, sampleFormat: "s16", channelCount: 1 });
1
+ import { request } from 'gaxios';
2
+ import * as FFMpegTranscoder from '../codecs/FFMpegTranscoder.js';
3
+ import { Logger } from '../utilities/Logger.js';
4
+ export async function recognize(rawAudio, apiKey, languageCode = 'en-US') {
5
+ const flac16Khz16bitMonoAudio = await FFMpegTranscoder.encodeFromChannels(rawAudio, { format: 'flac', sampleRate: 16000, sampleFormat: 's16', channelCount: 1 });
6
6
  const logger = new Logger();
7
- logger.start("Request recognition from Google Cloud");
7
+ logger.start('Request recognition from Google Cloud');
8
8
  const requestBody = {
9
9
  config: {
10
- encoding: "FLAC",
10
+ encoding: 'FLAC',
11
11
  sampleRateHertz: 16000,
12
12
  audioChannelCount: 1,
13
13
  languageCode,
@@ -17,33 +17,33 @@ export async function recognize(rawAudio, apiKey, languageCode = "en-US") {
17
17
  enableWordTimeOffsets: true,
18
18
  enableWordConfidence: true,
19
19
  enableAutomaticPunctuation: true,
20
- model: "latest_long",
20
+ model: 'latest_long',
21
21
  useEnhanced: true
22
22
  },
23
23
  audio: {
24
- content: flac16Khz16bitMonoAudio.toString("base64")
24
+ content: flac16Khz16bitMonoAudio.toString('base64')
25
25
  }
26
26
  };
27
27
  const response = await request({
28
- method: "POST",
28
+ method: 'POST',
29
29
  url: `https://speech.googleapis.com/v1p1beta1/speech:recognize`,
30
30
  params: {
31
- "key": apiKey
31
+ 'key': apiKey
32
32
  },
33
33
  headers: {
34
- "User-Agent": ""
34
+ 'User-Agent': ''
35
35
  },
36
36
  data: requestBody,
37
- responseType: "json"
37
+ responseType: 'json'
38
38
  });
39
- logger.start("Parse response body");
39
+ logger.start('Parse response body');
40
40
  const result = parseResponseBody(response.data);
41
41
  logger.end();
42
42
  return result;
43
43
  }
44
44
  function parseResponseBody(responseBody) {
45
45
  const results = responseBody.results;
46
- let transcript = "";
46
+ let transcript = '';
47
47
  const timeline = [];
48
48
  for (const result of results) {
49
49
  if (!result.alternatives || !result.alternatives[0] || !result.alternatives[0].transcript) {
@@ -53,10 +53,10 @@ function parseResponseBody(responseBody) {
53
53
  transcript += firstAlternative.transcript;
54
54
  for (const wordEvent of firstAlternative.words) {
55
55
  timeline.push({
56
- type: "word",
56
+ type: 'word',
57
57
  text: wordEvent.word,
58
- startTime: parseFloat(wordEvent.startTime.replace("s", "")),
59
- endTime: parseFloat(wordEvent.endTime.replace("s", "")),
58
+ startTime: parseFloat(wordEvent.startTime.replace('s', '')),
59
+ endTime: parseFloat(wordEvent.endTime.replace('s', '')),
60
60
  confidence: wordEvent.confidence
61
61
  });
62
62
  }
@@ -0,0 +1,19 @@
1
+ import { RawAudio } from '../audio/AudioUtilities.js';
2
+ import { Timeline } from '../utilities/Timeline.js';
3
+ export declare function recognize(rawAudio: RawAudio, languageCode: string, options: OpenAICloudSTTOptions, task?: Task): Promise<{
4
+ transcript: string;
5
+ timeline: Timeline;
6
+ }>;
7
+ export interface OpenAICloudSTTOptions {
8
+ model?: 'whisper-1';
9
+ apiKey?: string;
10
+ organization?: string;
11
+ baseURL?: string;
12
+ temperature?: number;
13
+ prompt?: string;
14
+ timeout?: number;
15
+ maxRetries?: number;
16
+ }
17
+ export declare const defaultOpenAICloudSTTOptions: OpenAICloudSTTOptions;
18
+ type Task = 'transcribe' | 'translate';
19
+ export {};
@@ -0,0 +1,81 @@
1
+ import * as FFMpegTranscoder from '../codecs/FFMpegTranscoder.js';
2
+ import { Logger } from '../utilities/Logger.js';
3
+ import { extendDeep } from '../utilities/ObjectUtilities.js';
4
+ export async function recognize(rawAudio, languageCode, options, task = 'transcribe') {
5
+ const logger = new Logger();
6
+ logger.start('Load OpenAI module');
7
+ options = extendDeep(defaultOpenAICloudSTTOptions, options);
8
+ const { default: OpenAI } = await import('openai');
9
+ const openai = new OpenAI(options);
10
+ logger.start('Encode audio to send');
11
+ const ffmpegOptions = FFMpegTranscoder.getDefaultFFMpegOptionsForSpeech('mp3');
12
+ const encodedAudio = await FFMpegTranscoder.encodeFromChannels(rawAudio, ffmpegOptions);
13
+ const audioAsWaveBlob = new FileLikeBlob([encodedAudio], 'audio', Date.now(), { type: 'audio/mpeg' });
14
+ logger.start('Request recognition from OpenAI Cloud API');
15
+ let response;
16
+ if (task == 'transcribe') {
17
+ response = await openai.audio.transcriptions.create({
18
+ file: audioAsWaveBlob,
19
+ model: options.model,
20
+ language: languageCode,
21
+ prompt: options.prompt,
22
+ response_format: 'verbose_json',
23
+ temperature: options.temperature,
24
+ timestamp_granularities: ['word', 'segment']
25
+ });
26
+ }
27
+ else if (task == 'translate') {
28
+ response = await openai.audio.translations.create({
29
+ file: audioAsWaveBlob,
30
+ model: options.model,
31
+ prompt: options.prompt,
32
+ response_format: 'verbose_json',
33
+ temperature: options.temperature,
34
+ });
35
+ }
36
+ else {
37
+ throw new Error(`Invalid task`);
38
+ }
39
+ const transcript = response.text;
40
+ let timeline;
41
+ if (response.words) {
42
+ timeline = response.words.map(entry => ({
43
+ type: 'word',
44
+ text: entry.word,
45
+ startTime: entry.start,
46
+ endTime: entry.end
47
+ }));
48
+ }
49
+ else {
50
+ timeline = response.segments.map(entry => ({
51
+ type: 'segment',
52
+ text: entry.text,
53
+ startTime: entry.start,
54
+ endTime: entry.end
55
+ }));
56
+ }
57
+ logger.end();
58
+ return { transcript, timeline };
59
+ }
60
+ class FileLikeBlob extends Blob {
61
+ parts;
62
+ name;
63
+ lastModified;
64
+ constructor(parts, name, lastModified, options) {
65
+ super(parts, options);
66
+ this.parts = parts;
67
+ this.name = name;
68
+ this.lastModified = lastModified;
69
+ }
70
+ }
71
+ export const defaultOpenAICloudSTTOptions = {
72
+ apiKey: undefined,
73
+ organization: undefined,
74
+ baseURL: undefined,
75
+ model: 'whisper-1',
76
+ temperature: 0,
77
+ prompt: undefined,
78
+ timeout: undefined,
79
+ maxRetries: 10,
80
+ };
81
+ //# sourceMappingURL=OpenAICloudSTT.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"OpenAICloudSTT.js","sourceRoot":"","sources":["../../src/recognition/OpenAICloudSTT.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,gBAAgB,MAAM,+BAA+B,CAAA;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAC;AAChD,OAAO,EAAE,UAAU,EAAE,MAAM,iCAAiC,CAAC;AAG7D,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,QAAkB,EAAE,YAAoB,EAAE,OAA8B,EAAE,OAAa,YAAY;IAClI,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAE3B,MAAM,CAAC,KAAK,CAAC,oBAAoB,CAAC,CAAA;IAElC,OAAO,GAAG,UAAU,CAAC,4BAA4B,EAAE,OAAO,CAAC,CAAA;IAE3D,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,GAAG,MAAM,MAAM,CAAC,QAAQ,CAAC,CAAA;IAClD,MAAM,MAAM,GAAG,IAAI,MAAM,CAAC,OAAO,CAAC,CAAA;IAElC,MAAM,CAAC,KAAK,CAAC,sBAAsB,CAAC,CAAA;IACpC,MAAM,aAAa,GAAG,gBAAgB,CAAC,gCAAgC,CAAC,KAAK,CAAC,CAAA;IAC9E,MAAM,YAAY,GAAG,MAAM,gBAAgB,CAAC,kBAAkB,CAAC,QAAQ,EAAE,aAAa,CAAC,CAAA;IACvF,MAAM,eAAe,GAAG,IAAI,YAAY,CAAC,CAAC,YAAY,CAAC,EAAE,OAAO,EAAE,IAAI,CAAC,GAAG,EAAE,EAAE,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC,CAAA;IAErG,MAAM,CAAC,KAAK,CAAC,2CAA2C,CAAC,CAAA;IAEzD,IAAI,QAAyB,CAAA;IAE7B,IAAI,IAAI,IAAG,YAAY,EAAE,CAAC;QACzB,QAAQ,GAAG,MAAM,MAAM,CAAC,KAAK,CAAC,cAAc,CAAC,MAAM,CAAC;YACnD,IAAI,EAAE,eAAe;YACrB,KAAK,EAAE,OAAO,CAAC,KAAM;YACrB,QAAQ,EAAE,YAAY;YACtB,MAAM,EAAE,OAAO,CAAC,MAAM;YACtB,eAAe,EAAE,cAAc;YAC/B,WAAW,EAAE,OAAO,CAAC,WAAW;YAChC,uBAAuB,EAAE,CAAC,MAAM,EAAE,SAAS,CAAC;SAC5C,CAAoB,CAAA;IACtB,CAAC;SAAM,IAAI,IAAI,IAAI,WAAW,EAAE,CAAC;QAChC,QAAQ,GAAG,MAAM,MAAM,CAAC,KAAK,CAAC,YAAY,CAAC,MAAM,CAAC;YACjD,IAAI,EAAE,eAAe;YACrB,KAAK,EAAE,OAAO,CAAC,KAAM;YACrB,MAAM,EAAE,OAAO,CAAC,MAAM;YACtB,eAAe,EAAE,cAAc;YAC/B,WAAW,EAAE,OAAO,CAAC,WAAW;SAChC,CAAoB,CAAA;IACtB,CAAC;SAAM,CAAC;QACP,MAAM,IAAI,KAAK,CAAC,cAAc,CAAC,CAAA;IAChC,CAAC;IAED,MAAM,UAAU,GAAG,QAAQ,CAAC,IAAI,CAAA;IAEhC,IAAI,QAAkB,CAAA;IAEtB,IAAI,QAAQ,CAAC,KAAK,EAAE,CAAC;QACpB,QAAQ,GAAG,QAAQ,CAAC,KAAK,CAAC,GAAG,CAAgB,KAAK,CAAC,EAAE,CAAC,CAAC;YACtD,IAAI,EAAE,MAAM;YACZ,IAAI,EAAE,KAAK,CAAC,IAAI;YAChB,SAAS,EAAE,KAAK,CAAC,KAAK;YACtB,OAAO,EAAE,KAAK,CAAC,GAAG;SAClB,CAAC,CAAC,CAAA;IACJ,CAAC;SAAM,CAAC;QACP,QAAQ,GAAG,QAAQ,CAAC,QAAQ,CAAC,GAAG,CAAgB,KAAK,CAAC,EAAE,CAAC,CAAC;YACzD,IAAI,EAAE,SAAS;YACf,IAAI,EAAE,KAAK,CAAC,IAAI;YAChB,SAAS,EAAE,KAAK,CAAC,KAAK;YACtB,OAAO,EAAE,KAAK,CAAC,GAAG;SAClB,CAAC,CAAC,CAAA;IACJ,CAAC;IAED,MAAM,CAAC,GAAG,EAAE,CAAA;IAEZ,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;AAChC,CAAC;AAED,MAAM,YAAa,SAAQ,IAAI;IAEb;IACA;IACA;IAHjB,YACiB,KAAiB,EACjB,IAAY,EACZ,YAAoB,EACpC,OAAwB;QAExB,KAAK,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QALL,UAAK,GAAL,KAAK,CAAY;QACjB,SAAI,GAAJ,IAAI,CAAQ;QACZ,iBAAY,GAAZ,YAAY,CAAQ;IAIrC,CAAC;CACD;AAgBD,MAAM,CAAC,MAAM,4BAA4B,GAA0B;IAClE,MAAM,EAAE,SAAS;IACjB,YAAY,EAAE,SAAS;IACvB,OAAO,EAAE,SAAS;IAElB,KAAK,EAAE,WAAW;IAClB,WAAW,EAAE,CAAC;IACd,MAAM,EAAE,SAAS;IAEjB,OAAO,EAAE,SAAS;IAClB,UAAU,EAAE,EAAE;CACd,CAAA"}
@@ -1,5 +1,5 @@
1
- import { Timeline } from "../utilities/Timeline.js";
2
- import { RawAudio } from "../audio/AudioUtilities.js";
1
+ import { Timeline } from '../utilities/Timeline.js';
2
+ import { RawAudio } from '../audio/AudioUtilities.js';
3
3
  export declare function recognize(rawAudio: RawAudio, modelDirectory: string): Promise<{
4
4
  transcript: string;
5
5
  timeline: Timeline;