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.
- package/README.md +15 -14
- package/data/schemas/options.json +398 -111
- package/dist/alignment/DTWMfccSequenceAlignment.d.ts +1 -1
- package/dist/alignment/DTWMfccSequenceAlignment.js +8 -8
- package/dist/alignment/DTWSequenceAlignment.d.ts +1 -1
- package/dist/alignment/DTWSequenceAlignment.js +1 -1
- package/dist/alignment/DTWSequenceAlignmentWindowed.d.ts +1 -1
- package/dist/alignment/DTWSequenceAlignmentWindowed.js +2 -2
- package/dist/alignment/LevenshteinSequenceAlignment.d.ts +1 -1
- package/dist/alignment/LevenshteinSequenceAlignment.js +1 -1
- package/dist/alignment/SpeechAlignment.d.ts +9 -10
- package/dist/alignment/SpeechAlignment.js +136 -105
- package/dist/alignment/SpeechAlignment.js.map +1 -1
- package/dist/api/API.d.ts +13 -12
- package/dist/api/API.js +14 -13
- package/dist/api/API.js.map +1 -1
- package/dist/api/APIOptions.d.ts +5 -4
- package/dist/api/Alignment.d.ts +15 -9
- package/dist/api/Alignment.js +88 -74
- package/dist/api/Alignment.js.map +1 -1
- package/dist/api/Common.js +1 -1
- package/dist/api/Denoising.d.ts +6 -6
- package/dist/api/Denoising.js +23 -23
- package/dist/api/Denoising.js.map +1 -1
- package/dist/api/LanguageDetection.d.ts +19 -12
- package/dist/api/LanguageDetection.js +88 -38
- package/dist/api/LanguageDetection.js.map +1 -1
- package/dist/api/Recognition.d.ts +16 -6
- package/dist/api/Recognition.js +129 -55
- package/dist/api/Recognition.js.map +1 -1
- package/dist/api/SourceSeparation.d.ts +17 -0
- package/dist/api/SourceSeparation.js +61 -0
- package/dist/api/SourceSeparation.js.map +1 -0
- package/dist/api/Synthesis.d.ts +18 -18
- package/dist/api/Synthesis.js +191 -164
- package/dist/api/Synthesis.js.map +1 -1
- package/dist/api/Translation.d.ts +19 -8
- package/dist/api/Translation.js +132 -35
- package/dist/api/Translation.js.map +1 -1
- package/dist/api/Vad.d.ts +10 -5
- package/dist/api/Vad.js +76 -38
- package/dist/api/Vad.js.map +1 -1
- package/dist/audio/AudioBufferConversion.d.ts +1 -1
- package/dist/audio/AudioBufferConversion.js +4 -4
- package/dist/audio/AudioPlayer.d.ts +1 -1
- package/dist/audio/AudioPlayer.js +26 -26
- package/dist/audio/AudioPlayer.js.map +1 -1
- package/dist/audio/AudioRecorder.d.ts +1 -1
- package/dist/audio/AudioRecorder.js +5 -5
- package/dist/audio/AudioUtilities.d.ts +13 -9
- package/dist/audio/AudioUtilities.js +86 -24
- package/dist/audio/AudioUtilities.js.map +1 -1
- package/dist/cli/CLI.d.ts +3 -3
- package/dist/cli/CLI.js +271 -162
- package/dist/cli/CLI.js.map +1 -1
- package/dist/cli/CLIConfigFile.js +8 -8
- package/dist/cli/CLILauncher.js +6 -6
- package/dist/cli/CLIOptionsSchema.js +2 -2
- package/dist/cli/CLIParser.js +5 -5
- package/dist/cli/CLIStarter.js +4 -4
- package/dist/codecs/FFMpegTranscoder.d.ts +2 -2
- package/dist/codecs/FFMpegTranscoder.js +37 -37
- package/dist/codecs/FFMpegTranscoder.js.map +1 -1
- package/dist/codecs/TIMITCodec.js +5 -5
- package/dist/codecs/WaveCodec.d.ts +1 -1
- package/dist/codecs/WaveCodec.js +22 -22
- package/dist/denoising/RNNoise.d.ts +1 -1
- package/dist/denoising/RNNoise.js +9 -9
- package/dist/dsp/BiquadFilter.d.ts +3 -2
- package/dist/dsp/BiquadFilter.js +18 -11
- package/dist/dsp/BiquadFilter.js.map +1 -1
- package/dist/dsp/DecayingPeakEstimator.d.ts +16 -0
- package/dist/dsp/DecayingPeakEstimator.js +23 -0
- package/dist/dsp/DecayingPeakEstimator.js.map +1 -0
- package/dist/dsp/FFT.d.ts +8 -4
- package/dist/dsp/FFT.js +76 -30
- package/dist/dsp/FFT.js.map +1 -1
- package/dist/dsp/KWeightingFilter.d.ts +9 -0
- package/dist/dsp/KWeightingFilter.js +40 -0
- package/dist/dsp/KWeightingFilter.js.map +1 -0
- package/dist/dsp/LoudnessEstimator.d.ts +21 -0
- package/dist/dsp/LoudnessEstimator.js +47 -0
- package/dist/dsp/LoudnessEstimator.js.map +1 -0
- package/dist/dsp/MFCC.d.ts +2 -2
- package/dist/dsp/MFCC.js +15 -15
- package/dist/dsp/MelSpectogram.d.ts +1 -1
- package/dist/dsp/MelSpectogram.js +6 -6
- package/dist/dsp/Rubberband.d.ts +11 -11
- package/dist/dsp/Rubberband.js +27 -27
- package/dist/dsp/Sonic.d.ts +1 -1
- package/dist/dsp/Sonic.js +3 -3
- package/dist/dsp/SpeexResampler.d.ts +1 -1
- package/dist/dsp/SpeexResampler.js +2 -2
- package/dist/math/VectorMath.d.ts +12 -8
- package/dist/math/VectorMath.js +35 -32
- package/dist/math/VectorMath.js.map +1 -1
- package/dist/nlp/ChineseSegmentation.js +2 -2
- package/dist/nlp/CompromiseNLP.js +3 -3
- package/dist/nlp/EspeakPhonemizer.js +30 -30
- package/dist/nlp/IPA.js +20 -20
- package/dist/nlp/JapaneseSegmentation.js +6 -6
- package/dist/nlp/Lexicon.d.ts +1 -1
- package/dist/nlp/Lexicon.js +7 -7
- package/dist/nlp/Segmentation.d.ts +3 -0
- package/dist/nlp/Segmentation.js +21 -14
- package/dist/nlp/Segmentation.js.map +1 -1
- package/dist/nlp/TextNormalizer.js +16 -16
- package/dist/recognition/AmazonTranscribeSTT.d.ts +2 -2
- package/dist/recognition/AmazonTranscribeSTT.js +13 -14
- package/dist/recognition/AmazonTranscribeSTT.js.map +1 -1
- package/dist/recognition/AzureCognitiveServicesSTT.js +5 -6
- package/dist/recognition/AzureCognitiveServicesSTT.js.map +1 -1
- package/dist/recognition/GoogleCloudSTT.d.ts +3 -3
- package/dist/recognition/GoogleCloudSTT.js +18 -18
- package/dist/recognition/OpenAICloudSTT.d.ts +19 -0
- package/dist/recognition/OpenAICloudSTT.js +81 -0
- package/dist/recognition/OpenAICloudSTT.js.map +1 -0
- package/dist/recognition/SileroSTT.d.ts +2 -2
- package/dist/recognition/SileroSTT.js +25 -25
- package/dist/recognition/VoskSTT.d.ts +2 -2
- package/dist/recognition/VoskSTT.js +8 -8
- package/dist/recognition/WhisperCppSTT.d.ts +88 -0
- package/dist/recognition/WhisperCppSTT.js +332 -0
- package/dist/recognition/WhisperCppSTT.js.map +1 -0
- package/dist/recognition/WhisperSTT.d.ts +49 -25
- package/dist/recognition/WhisperSTT.js +626 -481
- package/dist/recognition/WhisperSTT.js.map +1 -1
- package/dist/server/Client.d.ts +1 -1
- package/dist/server/Client.js +22 -22
- package/dist/server/Server.js +9 -9
- package/dist/server/Server.js.map +1 -1
- package/dist/server/Worker.d.ts +22 -22
- package/dist/server/Worker.js +36 -36
- package/dist/server/Worker.js.map +1 -1
- package/dist/server/WorkerStarter.js +2 -2
- package/dist/source-separation/MDXNetSourceSeparation.d.ts +11 -0
- package/dist/source-separation/MDXNetSourceSeparation.js +161 -0
- package/dist/source-separation/MDXNetSourceSeparation.js.map +1 -0
- package/dist/speech-language-detection/SileroLanguageDetection.d.ts +1 -1
- package/dist/speech-language-detection/SileroLanguageDetection.js +7 -7
- package/dist/subtitles/Subtitles.d.ts +10 -0
- package/dist/subtitles/Subtitles.js +2 -2
- package/dist/subtitles/Subtitles.js.map +1 -1
- package/dist/synthesis/AwsPollyTTS.d.ts +1 -1
- package/dist/synthesis/AwsPollyTTS.js +12 -12
- package/dist/synthesis/AzureCognitiveServicesTTS.js +7 -7
- package/dist/synthesis/CoquiServerTTS.js +10 -10
- package/dist/synthesis/CoquiServerTTS.js.map +1 -1
- package/dist/synthesis/ElevenlabsTTS.d.ts +23 -0
- package/dist/synthesis/ElevenlabsTTS.js +103 -0
- package/dist/synthesis/ElevenlabsTTS.js.map +1 -0
- package/dist/synthesis/EspeakTTS.d.ts +6 -5
- package/dist/synthesis/EspeakTTS.js +81 -69
- package/dist/synthesis/EspeakTTS.js.map +1 -1
- package/dist/synthesis/FliteTTS.d.ts +3 -3
- package/dist/synthesis/FliteTTS.js +154 -154
- package/dist/synthesis/FliteTTS.js.map +1 -1
- package/dist/synthesis/GoogleCloudTTS.d.ts +3 -3
- package/dist/synthesis/GoogleCloudTTS.js +17 -17
- package/dist/synthesis/GoogleCloudTTS.js.map +1 -1
- package/dist/synthesis/GoogleTranslateTTS.d.ts +1 -1
- package/dist/synthesis/GoogleTranslateTTS.js +103 -103
- package/dist/synthesis/MicrosoftEdgeTTS.d.ts +2 -2
- package/dist/synthesis/MicrosoftEdgeTTS.js +74 -74
- package/dist/synthesis/OpenAICloudTTS.d.ts +13 -0
- package/dist/synthesis/OpenAICloudTTS.js +169 -0
- package/dist/synthesis/OpenAICloudTTS.js.map +1 -0
- package/dist/synthesis/SamTTS.js +3 -3
- package/dist/synthesis/SapiTTS.d.ts +3 -3
- package/dist/synthesis/SapiTTS.js +26 -26
- package/dist/synthesis/StreamlabsPollyTTS.d.ts +2 -2
- package/dist/synthesis/StreamlabsPollyTTS.js +27 -27
- package/dist/synthesis/SvoxPicoTTS.d.ts +2 -2
- package/dist/synthesis/SvoxPicoTTS.js +65 -65
- package/dist/synthesis/SvoxPicoTTS.js.map +1 -1
- package/dist/synthesis/VitsTTS.d.ts +3 -3
- package/dist/synthesis/VitsTTS.js +378 -378
- package/dist/synthesis/VitsTTS.js.map +1 -1
- package/dist/tests/Test.js +2 -2
- package/dist/utilities/Compression.d.ts +5 -0
- package/dist/utilities/Compression.js +29 -13
- package/dist/utilities/Compression.js.map +1 -1
- package/dist/utilities/FileDownloader.d.ts +1 -1
- package/dist/utilities/FileDownloader.js +16 -16
- package/dist/utilities/FileSystem.js +7 -7
- package/dist/utilities/Locale.d.ts +7 -7
- package/dist/utilities/Locale.js +15 -15
- package/dist/utilities/Logger.js +3 -3
- package/dist/utilities/ObjectUtilities.js +19 -19
- package/dist/utilities/OpenPromise.js +2 -2
- package/dist/utilities/OpenPromise.js.map +1 -1
- package/dist/utilities/PackageManager.js +31 -0
- package/dist/utilities/PackageManager.js.map +1 -1
- package/dist/utilities/PathUtilities.js +8 -8
- package/dist/utilities/RandomGenerator.js +2 -2
- package/dist/utilities/SmoothEstimator.d.ts +8 -0
- package/dist/utilities/SmoothEstimator.js +25 -0
- package/dist/utilities/SmoothEstimator.js.map +1 -0
- package/dist/utilities/TarballMaker.js +8 -8
- package/dist/utilities/Timeline.d.ts +3 -2
- package/dist/utilities/Timeline.js +11 -11
- package/dist/utilities/Timeline.js.map +1 -1
- package/dist/utilities/Timer.js +4 -4
- package/dist/utilities/Utilities.d.ts +4 -0
- package/dist/utilities/Utilities.js +38 -15
- package/dist/utilities/Utilities.js.map +1 -1
- package/dist/utilities/WasmMemoryManager.js +7 -7
- package/dist/utilities/WebReader.js +23 -23
- package/dist/utilities/WikipediaReader.js +2 -2
- package/dist/voice-activity-detection/AdaptiveGateVAD.d.ts +28 -0
- package/dist/voice-activity-detection/AdaptiveGateVAD.js +138 -0
- package/dist/voice-activity-detection/AdaptiveGateVAD.js.map +1 -0
- package/dist/voice-activity-detection/SileroVAD.d.ts +1 -1
- package/dist/voice-activity-detection/SileroVAD.js +5 -5
- package/dist/voice-activity-detection/SileroVAD.js.map +1 -1
- package/dist/voice-activity-detection/WebRtcVAD.d.ts +1 -1
- package/dist/voice-activity-detection/WebRtcVAD.js +4 -4
- package/docs/API.md +29 -11
- package/docs/CLI.md +31 -7
- package/docs/Contributing.md +38 -0
- package/docs/Development.md +93 -19
- package/docs/Engines.md +28 -16
- package/docs/Licenses.md +4 -1
- package/docs/Options.md +158 -78
- package/docs/Releases.md +262 -0
- package/docs/Server.md +7 -7
- package/docs/Tasklist.md +95 -76
- package/docs/Technical.md +4 -4
- package/package.json +13 -14
- package/src/alignment/DTWMfccSequenceAlignment.ts +9 -9
- package/src/alignment/DTWSequenceAlignment.ts +2 -2
- package/src/alignment/DTWSequenceAlignmentWindowed.ts +3 -3
- package/src/alignment/LevenshteinSequenceAlignment.ts +2 -2
- package/src/alignment/SpeechAlignment.ts +204 -119
- package/src/api/API.ts +14 -13
- package/src/api/APIOptions.ts +12 -11
- package/src/api/Alignment.ts +147 -90
- package/src/api/Common.ts +1 -1
- package/src/api/Denoising.ts +28 -28
- package/src/api/LanguageDetection.ts +135 -48
- package/src/api/Recognition.ts +198 -59
- package/src/api/SourceSeparation.ts +99 -0
- package/src/api/Synthesis.ts +217 -181
- package/src/api/Translation.ts +193 -40
- package/src/api/Vad.ts +110 -41
- package/src/audio/AudioBufferConversion.ts +4 -4
- package/src/audio/AudioPlayer.ts +27 -27
- package/src/audio/AudioRecorder.ts +5 -5
- package/src/audio/AudioUtilities.ts +107 -24
- package/src/cli/CLI.ts +313 -164
- package/src/cli/CLIConfigFile.ts +8 -8
- package/src/cli/CLILauncher.ts +6 -6
- package/src/cli/CLIOptionsSchema.ts +2 -2
- package/src/cli/CLIParser.ts +5 -5
- package/src/cli/CLIStarter.ts +4 -4
- package/src/codecs/FFMpegTranscoder.ts +38 -38
- package/src/codecs/TIMITCodec.ts +5 -5
- package/src/codecs/WaveCodec.ts +22 -22
- package/src/denoising/RNNoise.ts +9 -9
- package/src/dsp/BiquadFilter.ts +19 -11
- package/src/dsp/DecayingPeakEstimator.ts +35 -0
- package/src/dsp/FFT.ts +103 -35
- package/src/dsp/KWeightingFilter.ts +43 -0
- package/src/dsp/LoudnessEstimator.ts +74 -0
- package/src/dsp/MFCC.ts +15 -15
- package/src/dsp/MelSpectogram.ts +7 -7
- package/src/dsp/Rubberband.ts +38 -38
- package/src/dsp/Sonic.ts +4 -4
- package/src/dsp/SpeexResampler.ts +2 -2
- package/src/math/VectorMath.ts +42 -33
- package/src/nlp/ChineseSegmentation.ts +3 -3
- package/src/nlp/CompromiseNLP.ts +3 -3
- package/src/nlp/EspeakPhonemizer.ts +30 -30
- package/src/nlp/IPA.ts +20 -20
- package/src/nlp/JapaneseSegmentation.ts +6 -6
- package/src/nlp/Lexicon.ts +8 -8
- package/src/nlp/Segmentation.ts +23 -14
- package/src/nlp/TextNormalizer.ts +16 -16
- package/src/recognition/AmazonTranscribeSTT.ts +16 -17
- package/src/recognition/AzureCognitiveServicesSTT.ts +8 -6
- package/src/recognition/GoogleCloudSTT.ts +21 -21
- package/src/recognition/OpenAICloudSTT.ts +142 -0
- package/src/recognition/SileroSTT.ts +26 -26
- package/src/recognition/VoskSTT.ts +10 -10
- package/src/recognition/WhisperCppSTT.ts +555 -0
- package/src/recognition/WhisperSTT.ts +760 -507
- package/src/server/Client.ts +23 -23
- package/src/server/Server.ts +9 -9
- package/src/server/Worker.ts +53 -53
- package/src/server/WorkerStarter.ts +2 -2
- package/src/source-separation/MDXNetSourceSeparation.ts +228 -0
- package/src/speech-language-detection/SileroLanguageDetection.ts +8 -8
- package/src/subtitles/Subtitles.ts +3 -3
- package/src/synthesis/AwsPollyTTS.ts +14 -14
- package/src/synthesis/AzureCognitiveServicesTTS.ts +10 -10
- package/src/synthesis/CoquiServerTTS.ts +10 -10
- package/src/synthesis/ElevenlabsTTS.ts +137 -0
- package/src/synthesis/EspeakTTS.ts +90 -71
- package/src/synthesis/FliteTTS.ts +157 -157
- package/src/synthesis/GoogleCloudTTS.ts +19 -19
- package/src/synthesis/GoogleTranslateTTS.ts +104 -104
- package/src/synthesis/MicrosoftEdgeTTS.ts +80 -80
- package/src/synthesis/OpenAICloudTTS.ts +196 -0
- package/src/synthesis/SamTTS.ts +3 -3
- package/src/synthesis/SapiTTS.ts +29 -29
- package/src/synthesis/StreamlabsPollyTTS.ts +29 -29
- package/src/synthesis/SvoxPicoTTS.ts +67 -67
- package/src/synthesis/VitsTTS.ts +380 -380
- package/src/tests/Test.ts +4 -4
- package/src/utilities/Compression.ts +34 -13
- package/src/utilities/FileDownloader.ts +19 -19
- package/src/utilities/FileSystem.ts +7 -7
- package/src/utilities/Locale.ts +22 -22
- package/src/utilities/Logger.ts +4 -4
- package/src/utilities/ObjectUtilities.ts +19 -19
- package/src/utilities/OpenPromise.ts +2 -2
- package/src/utilities/PackageManager.ts +40 -0
- package/src/utilities/PathUtilities.ts +8 -8
- package/src/utilities/RandomGenerator.ts +3 -3
- package/src/utilities/SmoothEstimator.ts +35 -0
- package/src/utilities/TarballMaker.ts +9 -9
- package/src/utilities/Timeline.ts +15 -13
- package/src/utilities/Timer.ts +4 -4
- package/src/utilities/Utilities.ts +49 -15
- package/src/utilities/WasmMemoryManager.ts +7 -7
- package/src/utilities/WebReader.ts +23 -23
- package/src/utilities/WikipediaReader.ts +2 -2
- package/src/voice-activity-detection/AdaptiveGateVAD.ts +202 -0
- package/src/voice-activity-detection/SileroVAD.ts +5 -5
- package/src/voice-activity-detection/WebRtcVAD.ts +5 -5
- package/dist/synthesis/ElevenLabsTTS.d.ts +0 -8
- package/dist/synthesis/ElevenLabsTTS.js +0 -82
- package/dist/synthesis/ElevenLabsTTS.js.map +0 -1
- package/src/synthesis/ElevenLabsTTS.ts +0 -104
package/src/synthesis/VitsTTS.ts
CHANGED
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
import type { InferenceSession } from 'onnxruntime-node'
|
|
2
2
|
import { SynthesisVoice } from '../api/API.js'
|
|
3
|
-
import { Logger } from
|
|
4
|
-
import { RawAudio, getEmptyRawAudio, getRawAudioDuration } from
|
|
5
|
-
import { Lexicon } from
|
|
6
|
-
import { Timeline } from
|
|
7
|
-
import { readAndParseJsonFile, readdir } from
|
|
3
|
+
import { Logger } from '../utilities/Logger.js'
|
|
4
|
+
import { RawAudio, getEmptyRawAudio, getRawAudioDuration } from '../audio/AudioUtilities.js'
|
|
5
|
+
import { Lexicon } from '../nlp/Lexicon.js'
|
|
6
|
+
import { Timeline } from '../utilities/Timeline.js'
|
|
7
|
+
import { readAndParseJsonFile, readdir } from '../utilities/FileSystem.js'
|
|
8
8
|
import path from 'node:path'
|
|
9
9
|
import { EspeakOptions, defaultEspeakOptions } from '../synthesis/EspeakTTS.js'
|
|
10
10
|
|
|
@@ -43,7 +43,7 @@ export class VitsTTS {
|
|
|
43
43
|
|
|
44
44
|
async initialize() {
|
|
45
45
|
const logger = new Logger()
|
|
46
|
-
await logger.startAsync(
|
|
46
|
+
await logger.startAsync('Initialize VITS ONNX synthesis model')
|
|
47
47
|
|
|
48
48
|
const onnxOptions: InferenceSession.SessionOptions = {
|
|
49
49
|
logSeverityLevel: 3
|
|
@@ -52,7 +52,7 @@ export class VitsTTS {
|
|
|
52
52
|
const { default: Onnx } = await import('onnxruntime-node')
|
|
53
53
|
|
|
54
54
|
const filesInModelPath = await readdir(this.modelPath)
|
|
55
|
-
const onnxModelFilename = filesInModelPath.find(filename => filename.endsWith(
|
|
55
|
+
const onnxModelFilename = filesInModelPath.find(filename => filename.endsWith('.onnx'))
|
|
56
56
|
|
|
57
57
|
if (!onnxModelFilename) {
|
|
58
58
|
throw new Error(`Couldn't file any ONNX model file in ${this.modelPath}`)
|
|
@@ -76,10 +76,10 @@ export class VitsTTS {
|
|
|
76
76
|
const logger = new Logger()
|
|
77
77
|
|
|
78
78
|
if (!this.modelSession) {
|
|
79
|
-
throw new Error(
|
|
79
|
+
throw new Error('Model has not been initialized')
|
|
80
80
|
}
|
|
81
81
|
|
|
82
|
-
await logger.startAsync(
|
|
82
|
+
await logger.startAsync('Prepare for synthesis')
|
|
83
83
|
|
|
84
84
|
const metadata = this.metadata
|
|
85
85
|
const phonemeMap = this.phonemeMap!
|
|
@@ -92,11 +92,11 @@ export class VitsTTS {
|
|
|
92
92
|
|
|
93
93
|
sentence = //simplifyPunctuationCharacters(sentence.trim())
|
|
94
94
|
sentence
|
|
95
|
-
.replaceAll(
|
|
96
|
-
.replaceAll(
|
|
97
|
-
.replaceAll(
|
|
95
|
+
.replaceAll('(', ', ')
|
|
96
|
+
.replaceAll(')', ', ')
|
|
97
|
+
.replaceAll('—', ', ')
|
|
98
98
|
|
|
99
|
-
const Espeak = await import(
|
|
99
|
+
const Espeak = await import('../synthesis/EspeakTTS.js')
|
|
100
100
|
|
|
101
101
|
logger.end()
|
|
102
102
|
|
|
@@ -114,21 +114,21 @@ export class VitsTTS {
|
|
|
114
114
|
}
|
|
115
115
|
}
|
|
116
116
|
|
|
117
|
-
await logger.startAsync(
|
|
117
|
+
await logger.startAsync('Encode phonemes to identifiers')
|
|
118
118
|
|
|
119
|
-
const clauseEndBreaker =
|
|
120
|
-
let sentenceEndBreaker =
|
|
119
|
+
const clauseEndBreaker = ','
|
|
120
|
+
let sentenceEndBreaker = '.'
|
|
121
121
|
|
|
122
|
-
if (sentence.endsWith(
|
|
123
|
-
sentenceEndBreaker =
|
|
124
|
-
} else if (sentence.endsWith(
|
|
125
|
-
sentenceEndBreaker =
|
|
122
|
+
if (sentence.endsWith('?') || sentence.endsWith(`?"`)) {
|
|
123
|
+
sentenceEndBreaker = '?'
|
|
124
|
+
} else if (sentence.endsWith('!') || sentence.endsWith(`!"`)) {
|
|
125
|
+
sentenceEndBreaker = '!'
|
|
126
126
|
}
|
|
127
127
|
|
|
128
|
-
const phonemeCharacterSeparatorId = phonemeMap.get(
|
|
129
|
-
const wordSeparatorId = phonemeMap.get(
|
|
130
|
-
const startId = phonemeMap.get(
|
|
131
|
-
const endId = phonemeMap.get(
|
|
128
|
+
const phonemeCharacterSeparatorId = phonemeMap.get('_')!
|
|
129
|
+
const wordSeparatorId = phonemeMap.get(' ')!
|
|
130
|
+
const startId = phonemeMap.get('^')!
|
|
131
|
+
const endId = phonemeMap.get('$')!
|
|
132
132
|
|
|
133
133
|
const clauseEndBreakerId = phonemeMap.get(clauseEndBreaker)!
|
|
134
134
|
const sentenceEndBreakerId = phonemeMap.get(sentenceEndBreaker)!
|
|
@@ -144,7 +144,7 @@ export class VitsTTS {
|
|
|
144
144
|
const id = phonemeMap.get(phonemeCharacter)
|
|
145
145
|
|
|
146
146
|
if (id == null) {
|
|
147
|
-
//logger.log(`No id found for subphoneme
|
|
147
|
+
//logger.log(`No id found for subphoneme '${char}'`)
|
|
148
148
|
continue
|
|
149
149
|
}
|
|
150
150
|
|
|
@@ -169,7 +169,7 @@ export class VitsTTS {
|
|
|
169
169
|
const bigIntIds = new BigInt64Array(ids.map(id => BigInt(id)))
|
|
170
170
|
const idLengths = new BigInt64Array([BigInt(bigIntIds.length)])
|
|
171
171
|
|
|
172
|
-
await logger.startAsync(
|
|
172
|
+
await logger.startAsync('Generate audio using synthesis model')
|
|
173
173
|
|
|
174
174
|
const { default: Onnx } = await import('onnxruntime-node')
|
|
175
175
|
|
|
@@ -181,15 +181,15 @@ export class VitsTTS {
|
|
|
181
181
|
const modelInputs = { input: inputTensor, input_lengths: inputLengthsTensor, scales: scalesTensor, sid: speakerIdTensor }
|
|
182
182
|
|
|
183
183
|
const modelResults = await this.modelSession.run(modelInputs)
|
|
184
|
-
const modelOutput = modelResults[
|
|
184
|
+
const modelOutput = modelResults['output']
|
|
185
185
|
|
|
186
186
|
const modelOutputAudioSamples = modelOutput['data'] as Float32Array
|
|
187
187
|
|
|
188
188
|
const synthesizedAudio: RawAudio = { audioChannels: [modelOutputAudioSamples], sampleRate: outputSampleRate }
|
|
189
189
|
|
|
190
|
-
await logger.startAsync(
|
|
190
|
+
await logger.startAsync('Align with reference synthesized audio')
|
|
191
191
|
|
|
192
|
-
const { alignUsingDtw } = await import(
|
|
192
|
+
const { alignUsingDtw } = await import('../alignment/SpeechAlignment.js')
|
|
193
193
|
|
|
194
194
|
const referenceWordTimeline = referenceTimeline.flatMap(clause => clause.timeline!)
|
|
195
195
|
|
|
@@ -204,645 +204,645 @@ export class VitsTTS {
|
|
|
204
204
|
|
|
205
205
|
export const voiceList: SynthesisVoice[] = [
|
|
206
206
|
{
|
|
207
|
-
name:
|
|
208
|
-
languages: [
|
|
209
|
-
gender:
|
|
207
|
+
name: 'ar_JO-kareem-low',
|
|
208
|
+
languages: ['ar-JO', 'ar'],
|
|
209
|
+
gender: 'male',
|
|
210
210
|
},
|
|
211
211
|
{
|
|
212
|
-
name:
|
|
213
|
-
languages: [
|
|
214
|
-
gender:
|
|
212
|
+
name: 'ar_JO-kareem-medium',
|
|
213
|
+
languages: ['ar-JO', 'ar'],
|
|
214
|
+
gender: 'male',
|
|
215
215
|
},
|
|
216
216
|
|
|
217
217
|
{
|
|
218
|
-
name:
|
|
219
|
-
languages: [
|
|
220
|
-
gender:
|
|
218
|
+
name: 'ca_ES-upc_ona-x_low',
|
|
219
|
+
languages: ['ca-ES', 'ca'],
|
|
220
|
+
gender: 'female',
|
|
221
221
|
},
|
|
222
222
|
{
|
|
223
|
-
name:
|
|
224
|
-
languages: [
|
|
225
|
-
gender:
|
|
223
|
+
name: 'ca_ES-upc_ona-medium',
|
|
224
|
+
languages: ['ca-ES', 'ca'],
|
|
225
|
+
gender: 'female',
|
|
226
226
|
},
|
|
227
227
|
{
|
|
228
|
-
name:
|
|
229
|
-
languages: [
|
|
230
|
-
gender:
|
|
228
|
+
name: 'ca_ES-upc_pau-x_low',
|
|
229
|
+
languages: ['ca-ES', 'ca'],
|
|
230
|
+
gender: 'male',
|
|
231
231
|
},
|
|
232
232
|
|
|
233
233
|
{
|
|
234
|
-
name:
|
|
235
|
-
languages: [
|
|
236
|
-
gender:
|
|
234
|
+
name: 'cs_CZ-jirka-low',
|
|
235
|
+
languages: ['cs-CZ', 'cs'],
|
|
236
|
+
gender: 'male',
|
|
237
237
|
},
|
|
238
238
|
{
|
|
239
|
-
name:
|
|
240
|
-
languages: [
|
|
241
|
-
gender:
|
|
239
|
+
name: 'cs_CZ-jirka-medium',
|
|
240
|
+
languages: ['cs-CZ', 'cs'],
|
|
241
|
+
gender: 'male',
|
|
242
242
|
},
|
|
243
243
|
|
|
244
244
|
{
|
|
245
|
-
name:
|
|
246
|
-
languages: [
|
|
247
|
-
gender:
|
|
245
|
+
name: 'da_DK-nst_talesyntese-medium',
|
|
246
|
+
languages: ['da-DK', 'da'],
|
|
247
|
+
gender: 'male',
|
|
248
248
|
},
|
|
249
249
|
|
|
250
250
|
{
|
|
251
|
-
name:
|
|
252
|
-
languages: [
|
|
253
|
-
gender:
|
|
251
|
+
name: 'de_DE-thorsten-low',
|
|
252
|
+
languages: ['de-DE', 'de'],
|
|
253
|
+
gender: 'male',
|
|
254
254
|
},
|
|
255
255
|
{
|
|
256
|
-
name:
|
|
257
|
-
languages: [
|
|
258
|
-
gender:
|
|
256
|
+
name: 'de_DE-thorsten-medium',
|
|
257
|
+
languages: ['de-DE', 'de'],
|
|
258
|
+
gender: 'male',
|
|
259
259
|
},
|
|
260
260
|
{
|
|
261
|
-
name:
|
|
262
|
-
languages: [
|
|
263
|
-
gender:
|
|
261
|
+
name: 'de_DE-thorsten_emotional-medium',
|
|
262
|
+
languages: ['de-DE', 'de'],
|
|
263
|
+
gender: 'male',
|
|
264
264
|
speakerCount: 8
|
|
265
265
|
},
|
|
266
266
|
{
|
|
267
|
-
name:
|
|
268
|
-
languages: [
|
|
269
|
-
gender:
|
|
267
|
+
name: 'de_DE-thorsten-high',
|
|
268
|
+
languages: ['de-DE', 'de'],
|
|
269
|
+
gender: 'male',
|
|
270
270
|
},
|
|
271
271
|
{
|
|
272
|
-
name:
|
|
273
|
-
languages: [
|
|
274
|
-
gender:
|
|
272
|
+
name: 'de_DE-eva_k-x_low',
|
|
273
|
+
languages: ['de-DE', 'de'],
|
|
274
|
+
gender: 'female',
|
|
275
275
|
},
|
|
276
276
|
{
|
|
277
|
-
name:
|
|
278
|
-
languages: [
|
|
279
|
-
gender:
|
|
277
|
+
name: 'de_DE-ramona-low',
|
|
278
|
+
languages: ['de-DE', 'de'],
|
|
279
|
+
gender: 'female',
|
|
280
280
|
},
|
|
281
281
|
{
|
|
282
|
-
name:
|
|
283
|
-
languages: [
|
|
284
|
-
gender:
|
|
282
|
+
name: 'de_DE-pavoque-low',
|
|
283
|
+
languages: ['de-DE', 'de'],
|
|
284
|
+
gender: 'male',
|
|
285
285
|
},
|
|
286
286
|
{
|
|
287
|
-
name:
|
|
288
|
-
languages: [
|
|
289
|
-
gender:
|
|
287
|
+
name: 'de_DE-kerstin-low',
|
|
288
|
+
languages: ['de-DE', 'de'],
|
|
289
|
+
gender: 'female',
|
|
290
290
|
},
|
|
291
291
|
{
|
|
292
|
-
name:
|
|
293
|
-
languages: [
|
|
294
|
-
gender:
|
|
292
|
+
name: 'de_DE-karlsson-low',
|
|
293
|
+
languages: ['de-DE', 'de'],
|
|
294
|
+
gender: 'male',
|
|
295
295
|
},
|
|
296
296
|
{
|
|
297
|
-
name:
|
|
298
|
-
languages: [
|
|
299
|
-
gender:
|
|
297
|
+
name: 'de_DE-mls-medium',
|
|
298
|
+
languages: ['de-DE', 'de'],
|
|
299
|
+
gender: 'unknown',
|
|
300
300
|
speakerCount: 236
|
|
301
301
|
},
|
|
302
302
|
|
|
303
303
|
{
|
|
304
|
-
name:
|
|
305
|
-
languages: [
|
|
306
|
-
gender:
|
|
304
|
+
name: 'el_GR-rapunzelina-low',
|
|
305
|
+
languages: ['el-GR', 'el'],
|
|
306
|
+
gender: 'female',
|
|
307
307
|
},
|
|
308
308
|
|
|
309
309
|
{
|
|
310
|
-
name:
|
|
311
|
-
languages: [
|
|
312
|
-
gender:
|
|
310
|
+
name: 'en_GB-alan-low',
|
|
311
|
+
languages: ['en-GB', 'en'],
|
|
312
|
+
gender: 'male',
|
|
313
313
|
},
|
|
314
314
|
{
|
|
315
|
-
name:
|
|
316
|
-
languages: [
|
|
317
|
-
gender:
|
|
315
|
+
name: 'en_GB-alan-medium',
|
|
316
|
+
languages: ['en-GB', 'en'],
|
|
317
|
+
gender: 'male',
|
|
318
318
|
},
|
|
319
319
|
{
|
|
320
|
-
name:
|
|
321
|
-
languages: [
|
|
322
|
-
gender:
|
|
320
|
+
name: 'en_GB-semaine-medium',
|
|
321
|
+
languages: ['en-GB', 'en'],
|
|
322
|
+
gender: 'unknown',
|
|
323
323
|
speakerCount: 4
|
|
324
324
|
},
|
|
325
325
|
{
|
|
326
|
-
name:
|
|
327
|
-
languages: [
|
|
328
|
-
gender:
|
|
326
|
+
name: 'en_GB-danny-low',
|
|
327
|
+
languages: ['en-GB', 'en'],
|
|
328
|
+
gender: 'male',
|
|
329
329
|
},
|
|
330
330
|
{
|
|
331
|
-
name:
|
|
332
|
-
languages: [
|
|
333
|
-
gender:
|
|
331
|
+
name: 'en_GB-alba-medium',
|
|
332
|
+
languages: ['en-GB', 'en'],
|
|
333
|
+
gender: 'female',
|
|
334
334
|
},
|
|
335
335
|
{
|
|
336
|
-
name:
|
|
337
|
-
languages: [
|
|
338
|
-
gender:
|
|
336
|
+
name: 'en_GB-aru-medium',
|
|
337
|
+
languages: ['en-GB', 'en'],
|
|
338
|
+
gender: 'unknown',
|
|
339
339
|
speakerCount: 12,
|
|
340
340
|
},
|
|
341
341
|
{
|
|
342
|
-
name:
|
|
343
|
-
languages: [
|
|
344
|
-
gender:
|
|
342
|
+
name: 'en_GB-southern_english_female-low',
|
|
343
|
+
languages: ['en-GB', 'en'],
|
|
344
|
+
gender: 'female',
|
|
345
345
|
},
|
|
346
346
|
{
|
|
347
|
-
name:
|
|
348
|
-
languages: [
|
|
349
|
-
gender:
|
|
347
|
+
name: 'en_GB-northern_english_male-medium',
|
|
348
|
+
languages: ['en-GB', 'en'],
|
|
349
|
+
gender: 'male',
|
|
350
350
|
},
|
|
351
351
|
{
|
|
352
|
-
name:
|
|
353
|
-
languages: [
|
|
354
|
-
gender:
|
|
352
|
+
name: 'en_GB-vctk-medium',
|
|
353
|
+
languages: ['en-GB', 'en'],
|
|
354
|
+
gender: 'unknown',
|
|
355
355
|
speakerCount: 109,
|
|
356
356
|
},
|
|
357
357
|
{
|
|
358
|
-
name:
|
|
359
|
-
languages: [
|
|
360
|
-
gender:
|
|
358
|
+
name: 'en_GB-jenny_dioco-medium',
|
|
359
|
+
languages: ['en-GB', 'en'],
|
|
360
|
+
gender: 'female',
|
|
361
361
|
},
|
|
362
362
|
{
|
|
363
|
-
name:
|
|
364
|
-
languages: [
|
|
365
|
-
gender:
|
|
363
|
+
name: 'en_GB-cori-high',
|
|
364
|
+
languages: ['en-GB', 'en'],
|
|
365
|
+
gender: 'female',
|
|
366
366
|
},
|
|
367
367
|
|
|
368
368
|
|
|
369
369
|
{
|
|
370
|
-
name:
|
|
371
|
-
languages: [
|
|
372
|
-
gender:
|
|
370
|
+
name: 'en_US-amy-low',
|
|
371
|
+
languages: ['en-US', 'en'],
|
|
372
|
+
gender: 'female',
|
|
373
373
|
},
|
|
374
374
|
{
|
|
375
|
-
name:
|
|
376
|
-
languages: [
|
|
377
|
-
gender:
|
|
375
|
+
name: 'en_US-amy-medium',
|
|
376
|
+
languages: ['en-US', 'en'],
|
|
377
|
+
gender: 'female',
|
|
378
378
|
},
|
|
379
379
|
{
|
|
380
|
-
name:
|
|
381
|
-
languages: [
|
|
382
|
-
gender:
|
|
380
|
+
name: 'en_US-kathleen-low',
|
|
381
|
+
languages: ['en-US', 'en'],
|
|
382
|
+
gender: 'female',
|
|
383
383
|
},
|
|
384
384
|
{
|
|
385
|
-
name:
|
|
386
|
-
languages: [
|
|
387
|
-
gender:
|
|
385
|
+
name: 'en_US-lessac-low',
|
|
386
|
+
languages: ['en-US', 'en'],
|
|
387
|
+
gender: 'female',
|
|
388
388
|
},
|
|
389
389
|
{
|
|
390
|
-
name:
|
|
391
|
-
languages: [
|
|
392
|
-
gender:
|
|
390
|
+
name: 'en_US-lessac-medium',
|
|
391
|
+
languages: ['en-US', 'en'],
|
|
392
|
+
gender: 'female',
|
|
393
393
|
},
|
|
394
394
|
{
|
|
395
|
-
name:
|
|
396
|
-
languages: [
|
|
397
|
-
gender:
|
|
395
|
+
name: 'en_US-lessac-high',
|
|
396
|
+
languages: ['en-US', 'en'],
|
|
397
|
+
gender: 'female',
|
|
398
398
|
},
|
|
399
399
|
{
|
|
400
|
-
name:
|
|
401
|
-
languages: [
|
|
402
|
-
gender:
|
|
400
|
+
name: 'en_US-libritts-high',
|
|
401
|
+
languages: ['en-US', 'en'],
|
|
402
|
+
gender: 'unknown',
|
|
403
403
|
speakerCount: 904,
|
|
404
404
|
},
|
|
405
405
|
{
|
|
406
|
-
name:
|
|
407
|
-
languages: [
|
|
408
|
-
gender:
|
|
406
|
+
name: 'en_US-libritts_r-medium',
|
|
407
|
+
languages: ['en-US', 'en'],
|
|
408
|
+
gender: 'unknown',
|
|
409
409
|
speakerCount: 904,
|
|
410
410
|
},
|
|
411
411
|
{
|
|
412
|
-
name:
|
|
413
|
-
languages: [
|
|
414
|
-
gender:
|
|
412
|
+
name: 'en_US-ryan-low',
|
|
413
|
+
languages: ['en-US', 'en'],
|
|
414
|
+
gender: 'male',
|
|
415
415
|
},
|
|
416
416
|
{
|
|
417
|
-
name:
|
|
418
|
-
languages: [
|
|
419
|
-
gender:
|
|
417
|
+
name: 'en_US-ryan-medium',
|
|
418
|
+
languages: ['en-US', 'en'],
|
|
419
|
+
gender: 'male',
|
|
420
420
|
},
|
|
421
421
|
{
|
|
422
|
-
name:
|
|
423
|
-
languages: [
|
|
424
|
-
gender:
|
|
422
|
+
name: 'en_US-ryan-high',
|
|
423
|
+
languages: ['en-US', 'en'],
|
|
424
|
+
gender: 'male',
|
|
425
425
|
},
|
|
426
426
|
{
|
|
427
|
-
name:
|
|
428
|
-
languages: [
|
|
429
|
-
gender:
|
|
427
|
+
name: 'en_US-joe-medium',
|
|
428
|
+
languages: ['en-US', 'en'],
|
|
429
|
+
gender: 'male',
|
|
430
430
|
},
|
|
431
431
|
{
|
|
432
|
-
name:
|
|
433
|
-
languages: [
|
|
434
|
-
gender:
|
|
432
|
+
name: 'en_US-kusal-medium',
|
|
433
|
+
languages: ['en-US', 'en'],
|
|
434
|
+
gender: 'male',
|
|
435
435
|
},
|
|
436
436
|
{
|
|
437
|
-
name:
|
|
438
|
-
languages: [
|
|
439
|
-
gender:
|
|
437
|
+
name: 'en_US-arctic-medium',
|
|
438
|
+
languages: ['en-US', 'en'],
|
|
439
|
+
gender: 'unknown',
|
|
440
440
|
speakerCount: 18
|
|
441
441
|
},
|
|
442
442
|
{
|
|
443
|
-
name:
|
|
444
|
-
languages: [
|
|
445
|
-
gender:
|
|
443
|
+
name: 'en_US-l2arctic-medium',
|
|
444
|
+
languages: ['en-US', 'en'],
|
|
445
|
+
gender: 'unknown',
|
|
446
446
|
speakerCount: 24
|
|
447
447
|
},
|
|
448
448
|
{
|
|
449
|
-
name:
|
|
450
|
-
languages: [
|
|
451
|
-
gender:
|
|
449
|
+
name: 'en_US-hfc_male-medium',
|
|
450
|
+
languages: ['en-US', 'en'],
|
|
451
|
+
gender: 'male',
|
|
452
452
|
},
|
|
453
453
|
{
|
|
454
|
-
name:
|
|
455
|
-
languages: [
|
|
456
|
-
gender:
|
|
454
|
+
name: 'en_US-hfc_female-medium',
|
|
455
|
+
languages: ['en-US', 'en'],
|
|
456
|
+
gender: 'female',
|
|
457
457
|
},
|
|
458
458
|
{
|
|
459
|
-
name:
|
|
460
|
-
languages: [
|
|
461
|
-
gender:
|
|
459
|
+
name: 'en_US-kristin-medium',
|
|
460
|
+
languages: ['en-US', 'en'],
|
|
461
|
+
gender: 'female',
|
|
462
462
|
},
|
|
463
463
|
{
|
|
464
|
-
name:
|
|
465
|
-
languages: [
|
|
466
|
-
gender:
|
|
464
|
+
name: 'en_US-ljspeech-high',
|
|
465
|
+
languages: ['en-US', 'en'],
|
|
466
|
+
gender: 'female',
|
|
467
467
|
},
|
|
468
468
|
{
|
|
469
|
-
name:
|
|
470
|
-
languages: [
|
|
471
|
-
gender:
|
|
469
|
+
name: 'en_US-ljspeech-medium',
|
|
470
|
+
languages: ['en-US', 'en'],
|
|
471
|
+
gender: 'female',
|
|
472
472
|
},
|
|
473
473
|
|
|
474
474
|
{
|
|
475
|
-
name:
|
|
476
|
-
languages: [
|
|
477
|
-
gender:
|
|
475
|
+
name: 'es_ES-carlfm-x_low',
|
|
476
|
+
languages: ['es-ES', 'es'],
|
|
477
|
+
gender: 'male',
|
|
478
478
|
},
|
|
479
479
|
{
|
|
480
|
-
name:
|
|
481
|
-
languages: [
|
|
482
|
-
gender:
|
|
480
|
+
name: 'es_ES-sharvard-medium',
|
|
481
|
+
languages: ['es-ES', 'es'],
|
|
482
|
+
gender: 'unknown',
|
|
483
483
|
speakerCount: 2
|
|
484
484
|
},
|
|
485
485
|
{
|
|
486
|
-
name:
|
|
487
|
-
languages: [
|
|
488
|
-
gender:
|
|
486
|
+
name: 'es_ES-davefx-medium',
|
|
487
|
+
languages: ['es-ES', 'es'],
|
|
488
|
+
gender: 'male',
|
|
489
489
|
},
|
|
490
490
|
{
|
|
491
|
-
name:
|
|
492
|
-
languages: [
|
|
493
|
-
gender:
|
|
491
|
+
name: 'es_ES-mls_9972-low',
|
|
492
|
+
languages: ['es-ES', 'es'],
|
|
493
|
+
gender: 'male',
|
|
494
494
|
},
|
|
495
495
|
{
|
|
496
|
-
name:
|
|
497
|
-
languages: [
|
|
498
|
-
gender:
|
|
496
|
+
name: 'es_ES-mls_10246-low',
|
|
497
|
+
languages: ['es-ES', 'es'],
|
|
498
|
+
gender: 'male',
|
|
499
499
|
},
|
|
500
500
|
|
|
501
501
|
{
|
|
502
|
-
name:
|
|
503
|
-
languages: [
|
|
504
|
-
gender:
|
|
502
|
+
name: 'es_MX-ald-medium',
|
|
503
|
+
languages: ['es-MX', 'es'],
|
|
504
|
+
gender: 'male',
|
|
505
505
|
},
|
|
506
506
|
{
|
|
507
|
-
name:
|
|
508
|
-
languages: [
|
|
509
|
-
gender:
|
|
507
|
+
name: 'es_MX-claude-high',
|
|
508
|
+
languages: ['es-MX', 'es'],
|
|
509
|
+
gender: 'female',
|
|
510
510
|
},
|
|
511
511
|
|
|
512
512
|
{
|
|
513
|
-
name:
|
|
514
|
-
languages: [
|
|
515
|
-
gender:
|
|
513
|
+
name: 'fa_IR-amir-medium',
|
|
514
|
+
languages: ['fa_IR', 'fa'],
|
|
515
|
+
gender: 'male',
|
|
516
516
|
},
|
|
517
517
|
{
|
|
518
|
-
name:
|
|
519
|
-
languages: [
|
|
520
|
-
gender:
|
|
518
|
+
name: 'fa_IR-gyro-medium',
|
|
519
|
+
languages: ['fa_IR', 'fa'],
|
|
520
|
+
gender: 'male',
|
|
521
521
|
},
|
|
522
522
|
|
|
523
523
|
|
|
524
524
|
{
|
|
525
|
-
name:
|
|
526
|
-
languages: [
|
|
527
|
-
gender:
|
|
525
|
+
name: 'fi_FI-harri-low',
|
|
526
|
+
languages: ['fi-FI', 'fi'],
|
|
527
|
+
gender: 'female',
|
|
528
528
|
},
|
|
529
529
|
{
|
|
530
|
-
name:
|
|
531
|
-
languages: [
|
|
532
|
-
gender:
|
|
530
|
+
name: 'fi_FI-harri-medium',
|
|
531
|
+
languages: ['fi-FI', 'fi'],
|
|
532
|
+
gender: 'female',
|
|
533
533
|
},
|
|
534
534
|
|
|
535
535
|
{
|
|
536
|
-
name:
|
|
537
|
-
languages: [
|
|
538
|
-
gender:
|
|
536
|
+
name: 'fr_FR-siwis-low',
|
|
537
|
+
languages: ['fr-FR', 'fr'],
|
|
538
|
+
gender: 'female',
|
|
539
539
|
},
|
|
540
540
|
{
|
|
541
|
-
name:
|
|
542
|
-
languages: [
|
|
543
|
-
gender:
|
|
541
|
+
name: 'fr_FR-siwis-medium',
|
|
542
|
+
languages: ['fr-FR', 'fr'],
|
|
543
|
+
gender: 'female',
|
|
544
544
|
},
|
|
545
545
|
{
|
|
546
|
-
name:
|
|
547
|
-
languages: [
|
|
548
|
-
gender:
|
|
546
|
+
name: 'fr_FR-mls_1840-low',
|
|
547
|
+
languages: ['fr-FR', 'fr'],
|
|
548
|
+
gender: 'male',
|
|
549
549
|
},
|
|
550
550
|
{
|
|
551
|
-
name:
|
|
552
|
-
languages: [
|
|
553
|
-
gender:
|
|
551
|
+
name: 'fr_FR-gilles-low',
|
|
552
|
+
languages: ['fr-FR', 'fr'],
|
|
553
|
+
gender: 'male',
|
|
554
554
|
},
|
|
555
555
|
{
|
|
556
|
-
name:
|
|
557
|
-
languages: [
|
|
558
|
-
gender:
|
|
556
|
+
name: 'fr_FR-upmc-medium',
|
|
557
|
+
languages: ['fr-FR', 'fr'],
|
|
558
|
+
gender: 'unknown',
|
|
559
559
|
speakerCount: 2
|
|
560
560
|
},
|
|
561
561
|
{
|
|
562
|
-
name:
|
|
563
|
-
languages: [
|
|
564
|
-
gender:
|
|
562
|
+
name: 'fr_FR-mls-medium',
|
|
563
|
+
languages: ['fr-FR', 'fr'],
|
|
564
|
+
gender: 'unknown',
|
|
565
565
|
speakerCount: 125
|
|
566
566
|
},
|
|
567
567
|
{
|
|
568
|
-
name:
|
|
569
|
-
languages: [
|
|
570
|
-
gender:
|
|
568
|
+
name: 'fr_FR-tom-medium',
|
|
569
|
+
languages: ['fr-FR', 'fr'],
|
|
570
|
+
gender: 'male',
|
|
571
571
|
},
|
|
572
572
|
|
|
573
573
|
{
|
|
574
|
-
name:
|
|
575
|
-
languages: [
|
|
576
|
-
gender:
|
|
574
|
+
name: 'hu_HU-anna-medium',
|
|
575
|
+
languages: ['hu-HU', 'hu'],
|
|
576
|
+
gender: 'female',
|
|
577
577
|
},
|
|
578
578
|
{
|
|
579
|
-
name:
|
|
580
|
-
languages: [
|
|
581
|
-
gender:
|
|
579
|
+
name: 'hu_HU-imre-medium',
|
|
580
|
+
languages: ['hu-HU', 'hu'],
|
|
581
|
+
gender: 'male',
|
|
582
582
|
},
|
|
583
583
|
|
|
584
584
|
{
|
|
585
|
-
name:
|
|
586
|
-
languages: [
|
|
587
|
-
gender:
|
|
585
|
+
name: 'is_IS-ugla-medium',
|
|
586
|
+
languages: ['is-IS', 'is'],
|
|
587
|
+
gender: 'female',
|
|
588
588
|
},
|
|
589
589
|
{
|
|
590
|
-
name:
|
|
591
|
-
languages: [
|
|
592
|
-
gender:
|
|
590
|
+
name: 'is_IS-steinn-medium',
|
|
591
|
+
languages: ['is-IS', 'is'],
|
|
592
|
+
gender: 'male',
|
|
593
593
|
},
|
|
594
594
|
{
|
|
595
|
-
name:
|
|
596
|
-
languages: [
|
|
597
|
-
gender:
|
|
595
|
+
name: 'is_IS-salka-medium',
|
|
596
|
+
languages: ['is-IS', 'is'],
|
|
597
|
+
gender: 'female',
|
|
598
598
|
},
|
|
599
599
|
{
|
|
600
|
-
name:
|
|
601
|
-
languages: [
|
|
602
|
-
gender:
|
|
600
|
+
name: 'is_IS-bui-medium',
|
|
601
|
+
languages: ['is-IS', 'is'],
|
|
602
|
+
gender: 'male',
|
|
603
603
|
},
|
|
604
604
|
|
|
605
605
|
{
|
|
606
|
-
name:
|
|
607
|
-
languages: [
|
|
608
|
-
gender:
|
|
606
|
+
name: 'it_IT-riccardo-x_low',
|
|
607
|
+
languages: ['it-IT', 'it'],
|
|
608
|
+
gender: 'male',
|
|
609
609
|
},
|
|
610
610
|
|
|
611
611
|
{
|
|
612
|
-
name:
|
|
613
|
-
languages: [
|
|
614
|
-
gender:
|
|
612
|
+
name: 'ka_GE-natia-medium',
|
|
613
|
+
languages: ['ka-GE', 'ka'],
|
|
614
|
+
gender: 'female',
|
|
615
615
|
},
|
|
616
616
|
|
|
617
617
|
{
|
|
618
|
-
name:
|
|
619
|
-
languages: [
|
|
620
|
-
gender:
|
|
618
|
+
name: 'kk_KZ-iseke-x_low',
|
|
619
|
+
languages: ['kk-KZ', 'kk'],
|
|
620
|
+
gender: 'male',
|
|
621
621
|
},
|
|
622
622
|
{
|
|
623
|
-
name:
|
|
624
|
-
languages: [
|
|
625
|
-
gender:
|
|
623
|
+
name: 'kk_KZ-raya-x_low',
|
|
624
|
+
languages: ['kk-KZ', 'kk'],
|
|
625
|
+
gender: 'male',
|
|
626
626
|
},
|
|
627
627
|
{
|
|
628
|
-
name:
|
|
629
|
-
languages: [
|
|
630
|
-
gender:
|
|
628
|
+
name: 'kk_KZ-issai-high',
|
|
629
|
+
languages: ['kk-KZ', 'kk'],
|
|
630
|
+
gender: 'unknown',
|
|
631
631
|
speakerCount: 6,
|
|
632
632
|
},
|
|
633
633
|
|
|
634
634
|
{
|
|
635
|
-
name:
|
|
636
|
-
languages: [
|
|
637
|
-
gender:
|
|
635
|
+
name: 'lb_LU-marylux-medium',
|
|
636
|
+
languages: ['lb-LU', 'lb'],
|
|
637
|
+
gender: 'female',
|
|
638
638
|
},
|
|
639
639
|
|
|
640
640
|
{
|
|
641
|
-
name:
|
|
642
|
-
languages: [
|
|
643
|
-
gender:
|
|
641
|
+
name: 'ne_NP-google-medium',
|
|
642
|
+
languages: ['ne-NP', 'ne'],
|
|
643
|
+
gender: 'female',
|
|
644
644
|
speakerCount: 18,
|
|
645
645
|
},
|
|
646
646
|
{
|
|
647
|
-
name:
|
|
648
|
-
languages: [
|
|
649
|
-
gender:
|
|
647
|
+
name: 'ne_NP-google-x_low',
|
|
648
|
+
languages: ['ne-NP', 'ne'],
|
|
649
|
+
gender: 'female',
|
|
650
650
|
speakerCount: 18,
|
|
651
651
|
},
|
|
652
652
|
|
|
653
653
|
{
|
|
654
|
-
name:
|
|
655
|
-
languages: [
|
|
656
|
-
gender:
|
|
654
|
+
name: 'nl_NL-mls_5809-low',
|
|
655
|
+
languages: ['nl-NL', 'nl'],
|
|
656
|
+
gender: 'female',
|
|
657
657
|
},
|
|
658
658
|
{
|
|
659
|
-
name:
|
|
660
|
-
languages: [
|
|
661
|
-
gender:
|
|
659
|
+
name: 'nl_NL-mls_7432-low',
|
|
660
|
+
languages: ['nl-NL', 'nl'],
|
|
661
|
+
gender: 'female',
|
|
662
662
|
},
|
|
663
663
|
{
|
|
664
|
-
name:
|
|
665
|
-
languages: [
|
|
666
|
-
gender:
|
|
664
|
+
name: 'nl_NL-mls-medium',
|
|
665
|
+
languages: ['nl-NL', 'nl'],
|
|
666
|
+
gender: 'unknown',
|
|
667
667
|
speakerCount: 52,
|
|
668
668
|
},
|
|
669
669
|
|
|
670
670
|
{
|
|
671
|
-
name:
|
|
672
|
-
languages: [
|
|
673
|
-
gender:
|
|
671
|
+
name: 'nl_BE-nathalie-x_low',
|
|
672
|
+
languages: ['nl-BE', 'nl'],
|
|
673
|
+
gender: 'female',
|
|
674
674
|
},
|
|
675
675
|
{
|
|
676
|
-
name:
|
|
677
|
-
languages: [
|
|
678
|
-
gender:
|
|
676
|
+
name: 'nl_BE-nathalie-medium',
|
|
677
|
+
languages: ['nl-BE', 'nl'],
|
|
678
|
+
gender: 'female',
|
|
679
679
|
},
|
|
680
680
|
{
|
|
681
|
-
name:
|
|
682
|
-
languages: [
|
|
683
|
-
gender:
|
|
681
|
+
name: 'nl_BE-rdh-medium',
|
|
682
|
+
languages: ['nl-BE', 'nl'],
|
|
683
|
+
gender: 'male',
|
|
684
684
|
},
|
|
685
685
|
{
|
|
686
|
-
name:
|
|
687
|
-
languages: [
|
|
688
|
-
gender:
|
|
686
|
+
name: 'nl_BE-rdh-x_low',
|
|
687
|
+
languages: ['nl-BE', 'nl'],
|
|
688
|
+
gender: 'male',
|
|
689
689
|
},
|
|
690
690
|
|
|
691
691
|
|
|
692
692
|
{
|
|
693
|
-
name:
|
|
694
|
-
languages: [
|
|
695
|
-
gender:
|
|
693
|
+
name: 'no_NO-talesyntese-medium',
|
|
694
|
+
languages: ['no-NO', 'no'],
|
|
695
|
+
gender: 'male',
|
|
696
696
|
},
|
|
697
697
|
|
|
698
698
|
{
|
|
699
|
-
name:
|
|
700
|
-
languages: [
|
|
701
|
-
gender:
|
|
699
|
+
name: 'pl_PL-mls_6892-low',
|
|
700
|
+
languages: ['pl-PL', 'pl'],
|
|
701
|
+
gender: 'male',
|
|
702
702
|
},
|
|
703
703
|
{
|
|
704
|
-
name:
|
|
705
|
-
languages: [
|
|
706
|
-
gender:
|
|
704
|
+
name: 'pl_PL-darkman-medium',
|
|
705
|
+
languages: ['pl-PL', 'pl'],
|
|
706
|
+
gender: 'male',
|
|
707
707
|
},
|
|
708
708
|
{
|
|
709
|
-
name:
|
|
710
|
-
languages: [
|
|
711
|
-
gender:
|
|
709
|
+
name: 'pl_PL-gosia-medium',
|
|
710
|
+
languages: ['pl-PL', 'pl'],
|
|
711
|
+
gender: 'female',
|
|
712
712
|
},
|
|
713
713
|
{
|
|
714
|
-
name:
|
|
715
|
-
languages: [
|
|
716
|
-
gender:
|
|
714
|
+
name: 'pl_PL-mc_speech-medium',
|
|
715
|
+
languages: ['pl-PL', 'pl'],
|
|
716
|
+
gender: 'male',
|
|
717
717
|
},
|
|
718
718
|
|
|
719
719
|
{
|
|
720
|
-
name:
|
|
721
|
-
languages: [
|
|
722
|
-
gender:
|
|
720
|
+
name: 'pt_BR-edresson-low',
|
|
721
|
+
languages: ['pt-BR', 'pt'],
|
|
722
|
+
gender: 'male',
|
|
723
723
|
},
|
|
724
724
|
{
|
|
725
|
-
name:
|
|
726
|
-
languages: [
|
|
727
|
-
gender:
|
|
725
|
+
name: 'pt_BR-faber-medium',
|
|
726
|
+
languages: ['pt-BR', 'pt'],
|
|
727
|
+
gender: 'male',
|
|
728
728
|
},
|
|
729
729
|
|
|
730
730
|
{
|
|
731
|
-
name:
|
|
732
|
-
languages: [
|
|
733
|
-
gender:
|
|
731
|
+
name: 'pt_PT-tugao-medium',
|
|
732
|
+
languages: ['pt-PT', 'pt'],
|
|
733
|
+
gender: 'male',
|
|
734
734
|
},
|
|
735
735
|
|
|
736
736
|
{
|
|
737
|
-
name:
|
|
738
|
-
languages: [
|
|
739
|
-
gender:
|
|
737
|
+
name: 'ro_RO-mihai-medium',
|
|
738
|
+
languages: ['ro-RO', 'ro'],
|
|
739
|
+
gender: 'male',
|
|
740
740
|
},
|
|
741
741
|
|
|
742
742
|
{
|
|
743
|
-
name:
|
|
744
|
-
languages: [
|
|
745
|
-
gender:
|
|
743
|
+
name: 'ru_RU-ruslan-medium',
|
|
744
|
+
languages: ['ru-RU', 'ru'],
|
|
745
|
+
gender: 'male',
|
|
746
746
|
},
|
|
747
747
|
{
|
|
748
|
-
name:
|
|
749
|
-
languages: [
|
|
750
|
-
gender:
|
|
748
|
+
name: 'ru_RU-irinia-medium',
|
|
749
|
+
languages: ['ru-RU', 'ru'],
|
|
750
|
+
gender: 'female',
|
|
751
751
|
},
|
|
752
752
|
{
|
|
753
|
-
name:
|
|
754
|
-
languages: [
|
|
755
|
-
gender:
|
|
753
|
+
name: 'ru_RU-denis-medium',
|
|
754
|
+
languages: ['ru-RU', 'ru'],
|
|
755
|
+
gender: 'male',
|
|
756
756
|
},
|
|
757
757
|
{
|
|
758
|
-
name:
|
|
759
|
-
languages: [
|
|
760
|
-
gender:
|
|
758
|
+
name: 'ru_RU-dmitri-medium',
|
|
759
|
+
languages: ['ru-RU', 'ru'],
|
|
760
|
+
gender: 'male',
|
|
761
761
|
},
|
|
762
762
|
|
|
763
763
|
{
|
|
764
|
-
name:
|
|
765
|
-
languages: [
|
|
766
|
-
gender:
|
|
764
|
+
name: 'sk_SK-lili-medium',
|
|
765
|
+
languages: ['sk-SK', 'sk'],
|
|
766
|
+
gender: 'female',
|
|
767
767
|
},
|
|
768
768
|
|
|
769
769
|
{
|
|
770
|
-
name:
|
|
771
|
-
languages: [
|
|
772
|
-
gender:
|
|
770
|
+
name: 'sl_SI-artur-medium',
|
|
771
|
+
languages: ['sl_SI', 'sl'],
|
|
772
|
+
gender: 'male',
|
|
773
773
|
},
|
|
774
774
|
|
|
775
775
|
{
|
|
776
|
-
name:
|
|
777
|
-
languages: [
|
|
778
|
-
gender:
|
|
776
|
+
name: 'sr_RS-serbski_institut-medium',
|
|
777
|
+
languages: ['sr-RS', 'sr'],
|
|
778
|
+
gender: 'male',
|
|
779
779
|
speakerCount: 2
|
|
780
780
|
},
|
|
781
781
|
|
|
782
782
|
{
|
|
783
|
-
name:
|
|
784
|
-
languages: [
|
|
785
|
-
gender:
|
|
783
|
+
name: 'sv_SE-nst-medium',
|
|
784
|
+
languages: ['sv-SE', 'sv'],
|
|
785
|
+
gender: 'male',
|
|
786
786
|
},
|
|
787
787
|
|
|
788
788
|
{
|
|
789
|
-
name:
|
|
790
|
-
languages: [
|
|
791
|
-
gender:
|
|
789
|
+
name: 'sw_CD-lanfrica-medium',
|
|
790
|
+
languages: ['sw-CD', 'sw'],
|
|
791
|
+
gender: 'male',
|
|
792
792
|
},
|
|
793
793
|
|
|
794
794
|
{
|
|
795
|
-
name:
|
|
796
|
-
languages: [
|
|
797
|
-
gender:
|
|
795
|
+
name: 'tr_TR-dfki-medium',
|
|
796
|
+
languages: ['tr-TR', 'tr'],
|
|
797
|
+
gender: 'male',
|
|
798
798
|
},
|
|
799
799
|
{
|
|
800
|
-
name:
|
|
801
|
-
languages: [
|
|
802
|
-
gender:
|
|
800
|
+
name: 'tr_TR-fahrettin-medium',
|
|
801
|
+
languages: ['tr-TR', 'tr'],
|
|
802
|
+
gender: 'male',
|
|
803
803
|
},
|
|
804
804
|
{
|
|
805
|
-
name:
|
|
806
|
-
languages: [
|
|
807
|
-
gender:
|
|
805
|
+
name: 'tr_TR-fettah-medium',
|
|
806
|
+
languages: ['tr-TR', 'tr'],
|
|
807
|
+
gender: 'male',
|
|
808
808
|
},
|
|
809
809
|
|
|
810
810
|
{
|
|
811
|
-
name:
|
|
812
|
-
languages: [
|
|
813
|
-
gender:
|
|
811
|
+
name: 'uk_UA-lada-x_low',
|
|
812
|
+
languages: ['uk-UA', 'uk'],
|
|
813
|
+
gender: 'female',
|
|
814
814
|
},
|
|
815
815
|
{
|
|
816
|
-
name:
|
|
817
|
-
languages: [
|
|
818
|
-
gender:
|
|
816
|
+
name: 'uk_UA-ukrainian_tts-medium',
|
|
817
|
+
languages: ['uk-UA', 'uk'],
|
|
818
|
+
gender: 'unknown',
|
|
819
819
|
speakerCount: 3,
|
|
820
820
|
},
|
|
821
821
|
{
|
|
822
|
-
name:
|
|
823
|
-
languages: [
|
|
824
|
-
gender:
|
|
822
|
+
name: 'vi_VN-vivos-x_low',
|
|
823
|
+
languages: ['vi-VN', 'vi'],
|
|
824
|
+
gender: 'unknown',
|
|
825
825
|
speakerCount: 65,
|
|
826
826
|
},
|
|
827
827
|
{
|
|
828
|
-
name:
|
|
829
|
-
languages: [
|
|
830
|
-
gender:
|
|
828
|
+
name: 'vi_VN-25hours-single-low',
|
|
829
|
+
languages: ['vi-VN', 'vi'],
|
|
830
|
+
gender: 'female',
|
|
831
831
|
},
|
|
832
832
|
{
|
|
833
|
-
name:
|
|
834
|
-
languages: [
|
|
835
|
-
gender:
|
|
833
|
+
name: 'vi_VN-vais1000-medium',
|
|
834
|
+
languages: ['vi-VN', 'vi'],
|
|
835
|
+
gender: 'female',
|
|
836
836
|
},
|
|
837
837
|
|
|
838
838
|
{
|
|
839
|
-
name:
|
|
840
|
-
languages: [
|
|
841
|
-
gender:
|
|
839
|
+
name: 'zh_CN-huayan-x_low',
|
|
840
|
+
languages: ['zh-CN', 'zh'],
|
|
841
|
+
gender: 'female',
|
|
842
842
|
},
|
|
843
843
|
{
|
|
844
|
-
name:
|
|
845
|
-
languages: [
|
|
846
|
-
gender:
|
|
844
|
+
name: 'zh_CN-huayan-medium',
|
|
845
|
+
languages: ['zh-CN', 'zh'],
|
|
846
|
+
gender: 'female',
|
|
847
847
|
},
|
|
848
848
|
]
|