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
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"Recognition.js","sourceRoot":"","sources":["../../src/api/Recognition.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,iCAAiC,CAAA;AAE5D,OAAO,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AACvD,OAAO,EAA8B,cAAc,EAAE,mBAAmB,EAAE,YAAY,EAAE,MAAM,4BAA4B,CAAA;AAC1H,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAE/C,OAAO,KAAK,GAAG,MAAM,UAAU,CAAA;AAC/B,OAAO,EAAY,4BAA4B,EAAE,qCAAqC,EAAE,MAAM,0BAA0B,CAAA;
|
|
1
|
+
{"version":3,"file":"Recognition.js","sourceRoot":"","sources":["../../src/api/Recognition.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,iCAAiC,CAAA;AAE5D,OAAO,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AACvD,OAAO,EAA8B,cAAc,EAAE,mBAAmB,EAAE,YAAY,EAAE,MAAM,4BAA4B,CAAA;AAC1H,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAE/C,OAAO,KAAK,GAAG,MAAM,UAAU,CAAA;AAC/B,OAAO,EAAY,4BAA4B,EAAE,qCAAqC,EAAE,MAAM,0BAA0B,CAAA;AAExH,OAAO,EAAE,0BAA0B,EAAE,oBAAoB,EAAE,qBAAqB,EAAE,MAAM,wBAAwB,CAAA;AAChH,OAAO,EAAE,WAAW,EAAE,MAAM,gCAAgC,CAAA;AAC5D,OAAO,KAAK,MAAM,OAAO,CAAA;AACzB,OAAO,EAAmB,0BAA0B,EAAE,MAAM,2BAA2B,CAAA;AACvF,OAAO,EAAyB,4BAA4B,EAAE,MAAM,kCAAkC,CAAA;AAGtG,MAAM,GAAG,GAAG,WAAW,CAAA;AAEvB,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,KAAuB,EAAE,OAA2B;IACnF,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAE3B,MAAM,cAAc,GAAG,MAAM,CAAC,YAAY,EAAE,CAAA;IAE5C,OAAO,GAAG,UAAU,CAAC,yBAAyB,EAAE,OAAO,CAAC,CAAA;IAExD,MAAM,aAAa,GAAG,MAAM,cAAc,CAAC,KAAK,CAAC,CAAA;IAEjD,IAAI,cAAwB,CAAA;IAC5B,IAAI,gBAAsC,CAAA;IAC1C,IAAI,kBAAwC,CAAA;IAE5C,IAAI,OAAO,CAAC,OAAO,EAAE,CAAC;QACrB,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;QACd,MAAM,CAAC,GAAG,EAAE,CAAC;QAEb,CAAC,EAAE,gBAAgB,EAAE,kBAAkB,EAAE,GAAG,MAAM,GAAG,CAAC,OAAO,CAAC,aAAa,EAAE,OAAO,CAAC,gBAAiB,CAAC,CAAC,CAAA;QAExG,MAAM,CAAC,GAAG,EAAE,CAAA;QACZ,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;QAEd,cAAc,GAAG,MAAM,cAAc,CAAC,gBAAgB,EAAE,KAAK,EAAE,CAAC,CAAC,CAAA;IAClE,CAAC;SAAM,CAAC;QACP,cAAc,GAAG,MAAM,cAAc,CAAC,aAAa,EAAE,KAAK,EAAE,CAAC,CAAC,CAAA;IAC/D,CAAC;IAED,IAAI,oBAA0C,CAAA;IAE9C,IAAI,OAAO,CAAC,IAAI,EAAE,CAAC;QAClB,MAAM,CAAC,KAAK,CAAC,qCAAqC,CAAC,CAAC;QACpD,CAAC,EAAE,QAAQ,EAAE,oBAAoB,EAAE,eAAe,EAAE,cAAc,EAAE,GAAG,MAAM,GAAG,CAAC,mBAAmB,CAAC,cAAc,EAAE,OAAO,CAAC,GAAI,CAAC,CAAC,CAAA;QAEnI,MAAM,CAAC,GAAG,EAAE,CAAA;IACb,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,yBAAyB,CAAC,CAAA;IAEvC,cAAc,GAAG,mBAAmB,CAAC,cAAc,CAAC,CAAA;IACpD,cAAc,CAAC,aAAa,CAAC,CAAC,CAAC,GAAG,YAAY,CAAC,cAAc,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,CAAA;IAE/E,MAAM,MAAM,GAAG,OAAO,CAAC,MAAO,CAAA;IAE9B,IAAI,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC,CAAC,oCAAoC;QAC5D,MAAM,CAAC,KAAK,CAAC,kDAAkD,CAAC,CAAA;QAChE,MAAM,EAAE,gBAAgB,EAAE,GAAG,MAAM,GAAG,CAAC,oBAAoB,CAAC,cAAc,EAAE,OAAO,CAAC,iBAAkB,CAAC,CAAA;QAEvG,MAAM,CAAC,GAAG,EAAE,CAAA;QACZ,MAAM,CAAC,gBAAgB,CAAC,mBAAmB,EAAE,0BAA0B,CAAC,gBAAgB,CAAC,CAAC,CAAA;QAE1F,OAAO,CAAC,QAAQ,GAAG,gBAAgB,CAAA;IACpC,CAAC;SAAM,CAAC;QACP,MAAM,CAAC,GAAG,EAAE,CAAA;QAEZ,MAAM,0BAA0B,GAAG,0BAA0B,CAAC,oBAAoB,CAAC,qBAAqB,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAA;QAE5H,MAAM,CAAC,gBAAgB,CAAC,oBAAoB,EAAE,0BAA0B,CAAC,CAAA;IAC1E,CAAC;IAED,MAAM,YAAY,GAAG,qBAAqB,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAA;IAC5D,MAAM,iBAAiB,GAAG,oBAAoB,CAAC,YAAY,CAAC,CAAA;IAE5D,IAAI,UAAkB,CAAA;IACtB,IAAI,QAA8B,CAAA;IAElC,MAAM,CAAC,KAAK,CAAC,QAAQ,MAAM,SAAS,CAAC,CAAA;IAErC,QAAQ,MAAM,EAAE,CAAC;QAChB,KAAK,SAAS,CAAC,CAAC,CAAC;YAChB,MAAM,UAAU,GAAG,MAAM,MAAM,CAAC,8BAA8B,CAAC,CAAA;YAE/D,MAAM,cAAc,GAAG,OAAO,CAAC,OAAQ,CAAA;YAEvC,MAAM,CAAC,GAAG,EAAE,CAAA;YAEZ,MAAM,EAAE,SAAS,EAAE,QAAQ,EAAE,GAAG,MAAM,UAAU,CAAC,uBAAuB,CAAC,cAAc,CAAC,KAAK,EAAE,iBAAiB,CAAC,CAAA;YAEjH,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,UAAU,CAAC,SAAS,CACrD,cAAc,EACd,SAAS,EACT,QAAQ,EACR,YAAY,EACZ,iBAAiB,EACjB,cAAc,CACd,CAAC,CAAA;YAEF,MAAK;QACN,CAAC;QAED,KAAK,aAAa,CAAC,CAAC,CAAC;YACpB,MAAM,aAAa,GAAG,MAAM,MAAM,CAAC,iCAAiC,CAAC,CAAA;YAErE,MAAM,iBAAiB,GAAG,OAAO,CAAC,UAAW,CAAA;YAE7C,MAAM,CAAC,GAAG,EAAE,CAAA;YAEZ,MAAM,EAAE,SAAS,EAAE,SAAS,EAAE,GAAG,MAAM,aAAa,CAAC,gBAAgB,CAAC,iBAAiB,CAAC,KAAK,EAAE,iBAAiB,CAAC,CAAA;YAEjH,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,aAAa,CAAC,SAAS,CACxD,cAAc,EACd,YAAY,EACZ,iBAAiB,EACjB,SAAS,EACT,SAAS,EACT,iBAAiB,CACjB,CAAC,CAAA;YAEF,MAAK;QACN,CAAC;QAED,KAAK,MAAM,CAAC,CAAC,CAAC;YACb,MAAM,OAAO,GAAG,MAAM,MAAM,CAAC,2BAA2B,CAAC,CAAA;YAEzD,IAAI,CAAC;gBACJ,MAAM,MAAM,CAAC,kBAAkB,CAAC,CAAA;YACjC,CAAC;YAAC,OAAO,CAAC,EAAE,CAAC;gBACZ,GAAG,CAAC,CAAC,CAAC,CAAA;gBACN,MAAM,IAAI,KAAK,CAAC,gLAAgL,CAAC,CAAA;YAClM,CAAC;YAED,MAAM,WAAW,GAAG,OAAO,CAAC,IAAK,CAAA;YAEjC,MAAM,SAAS,GAAG,WAAW,CAAC,SAAS,CAAA;YAEvC,IAAI,CAAC,SAAS,EAAE,CAAC;gBAChB,MAAM,IAAI,KAAK,CAAC,mIAAmI,CAAC,CAAA;YACrJ,CAAC;YAED,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,OAAO,CAAC,SAAS,CAAC,cAAc,EAAE,SAAS,EAAE,IAAI,CAAC,CAAC,CAAA;YAErF,MAAK;QACN,CAAC;QAED,KAAK,QAAQ,CAAC,CAAC,CAAC;YACf,MAAM,SAAS,GAAG,MAAM,MAAM,CAAC,6BAA6B,CAAC,CAAA;YAE7D,MAAM,aAAa,GAAG,OAAO,CAAC,MAAO,CAAA;YAErC,IAAI,SAAS,GAAG,aAAa,CAAC,SAAS,CAAA;YAEvC,IAAI,CAAC,SAAS,EAAE,CAAC;gBAChB,MAAM,WAAW,GAAG,SAAS,CAAC,yBAAyB,CAAC,iBAAiB,CAAC,CAAA;gBAE1E,IAAI,CAAC,WAAW,EAAE,CAAC;oBAClB,MAAM,IAAI,KAAK,CAAC,aAAa,iBAAiB,8BAA8B,CAAC,CAAA;gBAC9E,CAAC;gBAED,SAAS,GAAG,MAAM,WAAW,CAAC,WAAW,CAAC,CAAA;YAC3C,CAAC;YAED,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,SAAS,CAAC,SAAS,CAAC,cAAc,EAAE,SAAS,CAAC,CAAC,CAAA;YAEjF,MAAK;QACN,CAAC;QAED,KAAK,cAAc,CAAC,CAAC,CAAC;YACrB,MAAM,cAAc,GAAG,MAAM,MAAM,CAAC,kCAAkC,CAAC,CAAA;YAEvE,MAAM,MAAM,GAAG,OAAO,CAAC,WAAY,CAAC,MAAM,CAAA;YAE1C,IAAI,CAAC,MAAM,EAAE,CAAC;gBACb,MAAM,IAAI,KAAK,CAAC,kBAAkB,CAAC,CAAA;YACpC,CAAC;YAED,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,cAAc,CAAC,SAAS,CAAC,cAAc,EAAE,MAAM,EAAE,iBAAiB,CAAC,CAAC,CAAA;YAEtG,MAAK;QACN,CAAC;QAED,KAAK,iBAAiB,CAAC,CAAC,CAAC;YACxB,MAAM,yBAAyB,GAAG,MAAM,MAAM,CAAC,6CAA6C,CAAC,CAAA;YAE7F,MAAM,eAAe,GAAG,OAAO,CAAC,cAAe,CAAC,eAAe,CAAA;YAE/D,IAAI,CAAC,eAAe,EAAE,CAAC;gBACtB,MAAM,IAAI,KAAK,CAAC,8CAA8C,CAAC,CAAA;YAChE,CAAC;YAED,MAAM,aAAa,GAAG,OAAO,CAAC,cAAe,CAAC,aAAa,CAAA;YAE3D,IAAI,CAAC,aAAa,EAAE,CAAC;gBACpB,MAAM,IAAI,KAAK,CAAC,4CAA4C,CAAC,CAAA;YAC9D,CAAC;YAED,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,yBAAyB,CAAC,SAAS,CAAC,cAAc,EAAE,eAAe,EAAE,aAAa,EAAE,iBAAiB,CAAC,CAAC,CAAA;YAEzI,MAAK;QACN,CAAC;QAED,KAAK,mBAAmB,CAAC,CAAC,CAAC;YAC1B,MAAM,mBAAmB,GAAG,MAAM,MAAM,CAAC,uCAAuC,CAAC,CAAA;YAEjF,MAAM,MAAM,GAAG,OAAO,CAAC,gBAAiB,CAAC,MAAM,CAAA;YAE/C,IAAI,CAAC,MAAM,EAAE,CAAC;gBACb,MAAM,IAAI,KAAK,CAAC,sCAAsC,CAAC,CAAA;YACxD,CAAC;YAED,MAAM,WAAW,GAAG,OAAO,CAAC,gBAAiB,CAAC,WAAW,CAAA;YAEzD,IAAI,CAAC,WAAW,EAAE,CAAC;gBAClB,MAAM,IAAI,KAAK,CAAC,6CAA6C,CAAC,CAAA;YAC/D,CAAC;YAED,MAAM,eAAe,GAAG,OAAO,CAAC,gBAAiB,CAAC,eAAe,CAAA;YAEjE,IAAI,CAAC,eAAe,EAAE,CAAC;gBACtB,MAAM,IAAI,KAAK,CAAC,iDAAiD,CAAC,CAAA;YACnE,CAAC;YAED,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,mBAAmB,CAAC,SAAS,CAAC,cAAc,EAAE,iBAAiB,EAAE,MAAM,EAAE,WAAW,EAAE,eAAe,CAAC,CAAC,CAAA;YAEzI,MAAK;QACN,CAAC;QAED,KAAK,cAAc,CAAC,CAAC,CAAC;YACrB,MAAM,cAAc,GAAG,MAAM,MAAM,CAAC,kCAAkC,CAAC,CAAA;YAEvE,MAAM,qBAAqB,GAAG,OAAO,CAAC,WAAY,CAAA;YAElD,IAAI,CAAC,qBAAqB,CAAC,MAAM,EAAE,CAAC;gBACnC,MAAM,IAAI,KAAK,CAAC,kCAAkC,CAAC,CAAA;YACpD,CAAC;YAED,MAAM,CAAC,GAAG,EAAE,CAAC;YAEb,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,GAAG,MAAM,cAAc,CAAC,SAAS,CAAC,cAAc,EAAE,iBAAiB,EAAE,qBAAqB,CAAC,CAAC,CAAA;YAErH,MAAK;QACN,CAAC;QAED,OAAO,CAAC,CAAC,CAAC;YACT,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,MAAM,oBAAoB,CAAC,CAAA;QAC/D,CAAC;IACF,CAAC;IAED,0DAA0D;IAC1D,IAAI,CAAC,QAAQ,EAAE,CAAC;QACf,MAAM,CAAC,KAAK,CAAC,2BAA2B,CAAC,CAAA;QACzC,MAAM,gBAAgB,GAAyB,UAAU,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,YAAY,EAAE,CAAC,CAAA;QAExG,MAAM,EAAE,YAAY,EAAE,GAAG,MAAM,GAAG,CAAC,KAAK,CAAC,cAAc,EAAE,UAAU,EAAE,gBAAgB,CAAC,CAAA;QAEtF,QAAQ,GAAG,YAAY,CAAA;IACxB,CAAC;IAED,6FAA6F;IAC7F,IAAI,oBAAoB,IAAI,oBAAoB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC7D,GAAG,CAAC,iCAAiC,CAAC,QAAQ,EAAE,oBAAoB,CAAC,CAAA;IACtE,CAAC;IAED,mBAAmB;IACnB,4BAA4B,CAAC,QAAQ,EAAE,UAAU,CAAC,CAAA;IAElD,wBAAwB;IACxB,MAAM,EAAE,eAAe,EAAE,GAAG,MAAM,qCAAqC,CAAC,QAAQ,EAAE,UAAU,EAAE,YAAY,EAAE,QAAQ,EAAE,UAAU,CAAC,CAAA;IAEjI,MAAM,CAAC,GAAG,EAAE,CAAA;IACZ,MAAM,CAAC,WAAW,CAAC,wBAAwB,EAAE,cAAc,EAAE,KAAK,CAAC,aAAa,CAAC,CAAA;IAEjF,OAAO;QACN,UAAU;QAEV,QAAQ,EAAE,eAAe;QACzB,YAAY,EAAE,QAAQ;QAEtB,QAAQ,EAAE,YAAY;QAEtB,aAAa;QACb,gBAAgB;QAChB,kBAAkB;KAClB,CAAA;AACF,CAAC;AAsED,MAAM,CAAC,MAAM,yBAAyB,GAAuB;IAC5D,MAAM,EAAE,SAAS;IAEjB,QAAQ,EAAE,SAAS;IAEnB,eAAe,EAAE,CAAC;IAElB,OAAO,EAAE,KAAK;IAEd,IAAI,EAAE,IAAI;IAEV,SAAS,EAAE,EACV;IAED,iBAAiB,EAAE,EAClB;IAED,SAAS,EAAE,0BAA0B;IAErC,GAAG,EAAE;QACJ,MAAM,EAAE,eAAe;KACvB;IAED,OAAO,EAAE,EACR;IAED,UAAU,EAAE,EACX;IAED,IAAI,EAAE;QACL,SAAS,EAAE,SAAS;KACpB;IAED,MAAM,EAAE;QACP,SAAS,EAAE,SAAS;KACpB;IAED,WAAW,EAAE;QACZ,MAAM,EAAE,SAAS;QACjB,wBAAwB,EAAE,EAAE;QAC5B,eAAe,EAAE,KAAK;QACtB,eAAe,EAAE,IAAI;QACrB,gBAAgB,EAAE,IAAI;KACtB;IAED,cAAc,EAAE;QACf,eAAe,EAAE,SAAS;QAC1B,aAAa,EAAE,SAAS;KACxB;IAED,gBAAgB,EAAE;QACjB,MAAM,EAAE,SAAS;QACjB,WAAW,EAAE,SAAS;QACtB,eAAe,EAAE,SAAS;KAC1B;IAED,WAAW,EAAE,4BAA4B;CACzC,CAAA;AAED,MAAM,CAAC,MAAM,kBAAkB,GAAyB;IACvD;QACC,EAAE,EAAE,SAAS;QACb,IAAI,EAAE,gBAAgB;QACtB,WAAW,EAAE,8EAA8E;QAC3F,IAAI,EAAE,OAAO;KACb;IACD;QACC,EAAE,EAAE,aAAa;QACjB,IAAI,EAAE,2BAA2B;QACjC,WAAW,EAAE,4DAA4D;QACzE,IAAI,EAAE,OAAO;KACb;IACD;QACC,EAAE,EAAE,MAAM;QACV,IAAI,EAAE,MAAM;QACZ,WAAW,EAAE,+BAA+B;QAC5C,IAAI,EAAE,OAAO;KACb;IACD;QACC,EAAE,EAAE,QAAQ;QACZ,IAAI,EAAE,QAAQ;QACd,WAAW,EAAE,4BAA4B;QACzC,IAAI,EAAE,OAAO;KACb;IACD;QACC,EAAE,EAAE,cAAc;QAClB,IAAI,EAAE,cAAc;QACpB,WAAW,EAAE,sCAAsC;QACnD,IAAI,EAAE,OAAO;KACb;IACD;QACC,EAAE,EAAE,iBAAiB;QACrB,IAAI,EAAE,0BAA0B;QAChC,WAAW,EAAE,yCAAyC;QACtD,IAAI,EAAE,OAAO;KACb;IACD;QACC,EAAE,EAAE,mBAAmB;QACvB,IAAI,EAAE,mBAAmB;QACzB,WAAW,EAAE,sCAAsC;QACnD,IAAI,EAAE,OAAO;KACb;IACD;QACC,EAAE,EAAE,cAAc;QAClB,IAAI,EAAE,cAAc;QACpB,WAAW,EAAE,sCAAsC;QACnD,IAAI,EAAE,OAAO;KACb;CACD,CAAA"}
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
import { AudioSourceParam, RawAudio } from '../audio/AudioUtilities.js';
|
|
2
|
+
import { EngineMetadata } from './Common.js';
|
|
3
|
+
export declare function isolate(input: AudioSourceParam, options: SourceSeparationOptions): Promise<SourceSeparationResult>;
|
|
4
|
+
export type SourceSeparationEngine = 'mdx-net';
|
|
5
|
+
export interface SourceSeparationOptions {
|
|
6
|
+
engine?: SourceSeparationEngine;
|
|
7
|
+
mdxNet?: {
|
|
8
|
+
model?: string;
|
|
9
|
+
};
|
|
10
|
+
}
|
|
11
|
+
export declare const defaultSourceSeparationOptions: SourceSeparationOptions;
|
|
12
|
+
export interface SourceSeparationResult {
|
|
13
|
+
inputRawAudio: RawAudio;
|
|
14
|
+
isolatedRawAudio: RawAudio;
|
|
15
|
+
backgroundRawAudio: RawAudio;
|
|
16
|
+
}
|
|
17
|
+
export declare const sourceSeparationEngines: EngineMetadata[];
|
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
import { ensureRawAudio, subtractAudio } from '../audio/AudioUtilities.js';
|
|
2
|
+
import { Logger } from '../utilities/Logger.js';
|
|
3
|
+
import { extendDeep } from '../utilities/ObjectUtilities.js';
|
|
4
|
+
import { loadPackage } from '../utilities/PackageManager.js';
|
|
5
|
+
import chalk from 'chalk';
|
|
6
|
+
import { readdir } from '../utilities/FileSystem.js';
|
|
7
|
+
import path from 'node:path';
|
|
8
|
+
export async function isolate(input, options) {
|
|
9
|
+
const logger = new Logger();
|
|
10
|
+
const startTimestamp = logger.getTimestamp();
|
|
11
|
+
logger.start('Prepare for source separation');
|
|
12
|
+
const inputRawAudio = await ensureRawAudio(input);
|
|
13
|
+
let isolatedRawAudio;
|
|
14
|
+
let backgroundRawAudio;
|
|
15
|
+
options = extendDeep(defaultSourceSeparationOptions, options);
|
|
16
|
+
switch (options.engine) {
|
|
17
|
+
case 'mdx-net': {
|
|
18
|
+
const MDXNetSourceSeparation = await import('../source-separation/MDXNetSourceSeparation.js');
|
|
19
|
+
const mdxNetOptions = options.mdxNet;
|
|
20
|
+
const packageDir = await loadPackage(`mdxnet-${mdxNetOptions.model}`);
|
|
21
|
+
const modelFilename = (await readdir(packageDir)).filter(name => name.endsWith('onnx'))[0];
|
|
22
|
+
if (!modelFilename) {
|
|
23
|
+
throw new Error(`Couldn't find an ONNX model file in package directory`);
|
|
24
|
+
}
|
|
25
|
+
const modelPath = path.join(packageDir, modelFilename);
|
|
26
|
+
logger.end();
|
|
27
|
+
const audioStereo44100 = await ensureRawAudio(inputRawAudio, 44100, 2);
|
|
28
|
+
isolatedRawAudio = await MDXNetSourceSeparation.isolate(audioStereo44100, modelPath);
|
|
29
|
+
logger.end();
|
|
30
|
+
logger.start(`Subtract from original waveform to extract background audio`);
|
|
31
|
+
backgroundRawAudio = subtractAudio(audioStereo44100, isolatedRawAudio);
|
|
32
|
+
break;
|
|
33
|
+
}
|
|
34
|
+
default: {
|
|
35
|
+
throw new Error(`Engine '${options.engine}' is not supported`);
|
|
36
|
+
}
|
|
37
|
+
}
|
|
38
|
+
logger.end();
|
|
39
|
+
logger.log('');
|
|
40
|
+
logger.logDuration(`Total source separation time`, startTimestamp, chalk.magentaBright);
|
|
41
|
+
return {
|
|
42
|
+
inputRawAudio,
|
|
43
|
+
isolatedRawAudio,
|
|
44
|
+
backgroundRawAudio
|
|
45
|
+
};
|
|
46
|
+
}
|
|
47
|
+
export const defaultSourceSeparationOptions = {
|
|
48
|
+
engine: 'mdx-net',
|
|
49
|
+
mdxNet: {
|
|
50
|
+
model: 'UVR_MDXNET_1_9703'
|
|
51
|
+
}
|
|
52
|
+
};
|
|
53
|
+
export const sourceSeparationEngines = [
|
|
54
|
+
{
|
|
55
|
+
id: 'mdx-net',
|
|
56
|
+
name: 'MDX-NET',
|
|
57
|
+
description: 'Deep learning source separation architecture by KUIELAB (Korea University).',
|
|
58
|
+
type: 'local'
|
|
59
|
+
},
|
|
60
|
+
];
|
|
61
|
+
//# sourceMappingURL=SourceSeparation.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"SourceSeparation.js","sourceRoot":"","sources":["../../src/api/SourceSeparation.ts"],"names":[],"mappings":"AAAA,OAAO,EAA8B,cAAc,EAAE,aAAa,EAAE,MAAM,4BAA4B,CAAC;AACvG,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAC;AAChD,OAAO,EAAE,UAAU,EAAE,MAAM,iCAAiC,CAAC;AAC7D,OAAO,EAAE,WAAW,EAAE,MAAM,gCAAgC,CAAC;AAE7D,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAC;AACrD,OAAO,IAAI,MAAM,WAAW,CAAC;AAE7B,MAAM,CAAC,KAAK,UAAU,OAAO,CAAC,KAAuB,EAAE,OAAgC;IACtF,MAAM,MAAM,GAAG,IAAI,MAAM,EAAE,CAAA;IAC3B,MAAM,cAAc,GAAG,MAAM,CAAC,YAAY,EAAE,CAAA;IAE5C,MAAM,CAAC,KAAK,CAAC,+BAA+B,CAAC,CAAA;IAE7C,MAAM,aAAa,GAAG,MAAM,cAAc,CAAC,KAAK,CAAC,CAAA;IAEjD,IAAI,gBAA0B,CAAA;IAC9B,IAAI,kBAA4B,CAAA;IAEhC,OAAO,GAAG,UAAU,CAAC,8BAA8B,EAAE,OAAO,CAAC,CAAA;IAE7D,QAAQ,OAAO,CAAC,MAAM,EAAE,CAAC;QACxB,KAAK,SAAS,CAAC,CAAC,CAAC;YAChB,MAAM,sBAAsB,GAAG,MAAM,MAAM,CAAC,gDAAgD,CAAC,CAAA;YAE7F,MAAM,aAAa,GAAG,OAAO,CAAC,MAAO,CAAA;YAErC,MAAM,UAAU,GAAG,MAAM,WAAW,CAAC,UAAU,aAAa,CAAC,KAAM,EAAE,CAAC,CAAA;YACtE,MAAM,aAAa,GAAG,CAAC,MAAM,OAAO,CAAC,UAAU,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;YAE1F,IAAI,CAAC,aAAa,EAAE,CAAC;gBACpB,MAAM,IAAI,KAAK,CAAC,uDAAuD,CAAC,CAAA;YACzE,CAAC;YAED,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,UAAU,EAAE,aAAa,CAAC,CAAA;YAEtD,MAAM,CAAC,GAAG,EAAE,CAAA;YAEZ,MAAM,gBAAgB,GAAG,MAAM,cAAc,CAAC,aAAa,EAAE,KAAK,EAAE,CAAC,CAAC,CAAA;YAEtE,gBAAgB,GAAG,MAAM,sBAAsB,CAAC,OAAO,CAAC,gBAAgB,EAAE,SAAS,CAAC,CAAA;YAEpF,MAAM,CAAC,GAAG,EAAE,CAAA;YAEZ,MAAM,CAAC,KAAK,CAAC,6DAA6D,CAAC,CAAA;YAC3E,kBAAkB,GAAG,aAAa,CAAC,gBAAgB,EAAE,gBAAgB,CAAC,CAAA;YAEtE,MAAK;QACN,CAAC;QAED,OAAO,CAAC,CAAC,CAAC;YACT,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,MAAM,oBAAoB,CAAC,CAAA;QAC/D,CAAC;IACF,CAAC;IAED,MAAM,CAAC,GAAG,EAAE,CAAA;IACZ,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;IACd,MAAM,CAAC,WAAW,CAAC,8BAA8B,EAAE,cAAc,EAAE,KAAK,CAAC,aAAa,CAAC,CAAA;IAEvF,OAAO;QACN,aAAa;QACb,gBAAgB;QAChB,kBAAkB;KAClB,CAAA;AACF,CAAC;AAYD,MAAM,CAAC,MAAM,8BAA8B,GAA4B;IACtE,MAAM,EAAE,SAAS;IAEjB,MAAM,EAAE;QACP,KAAK,EAAE,mBAAmB;KAC1B;CACD,CAAA;AAQD,MAAM,CAAC,MAAM,uBAAuB,GAAqB;IACxD;QACC,EAAE,EAAE,SAAS;QACb,IAAI,EAAE,SAAS;QACf,WAAW,EAAE,6EAA6E;QAC1F,IAAI,EAAE,OAAO;KACb;CACD,CAAA"}
|
package/dist/api/Synthesis.d.ts
CHANGED
|
@@ -1,10 +1,12 @@
|
|
|
1
1
|
/// <reference types="node" resolution-mode="require"/>
|
|
2
|
-
import { RawAudio } from
|
|
3
|
-
import { type RubberbandOptions } from
|
|
4
|
-
import * as API from
|
|
5
|
-
import { Timeline } from
|
|
6
|
-
import { EngineMetadata } from
|
|
7
|
-
import { SubtitlesConfig } from
|
|
2
|
+
import { RawAudio } from '../audio/AudioUtilities.js';
|
|
3
|
+
import { type RubberbandOptions } from '../dsp/Rubberband.js';
|
|
4
|
+
import * as API from './API.js';
|
|
5
|
+
import { Timeline } from '../utilities/Timeline.js';
|
|
6
|
+
import { EngineMetadata } from './Common.js';
|
|
7
|
+
import { SubtitlesConfig } from '../subtitles/Subtitles.js';
|
|
8
|
+
import { OpenAICloudTTSOptions } from '../synthesis/OpenAICloudTTS.js';
|
|
9
|
+
import { ElevenlabsTTSOptions } from '../synthesis/ElevenlabsTTS.js';
|
|
8
10
|
export declare function synthesize(input: string | string[], options: SynthesisOptions, onSegment?: SynthesisSegmentEvent, onSentence?: SynthesisSegmentEvent): Promise<SynthesisResult>;
|
|
9
11
|
export interface SynthesisResult {
|
|
10
12
|
audio: RawAudio | Buffer;
|
|
@@ -12,8 +14,8 @@ export interface SynthesisResult {
|
|
|
12
14
|
language: string;
|
|
13
15
|
voice: string;
|
|
14
16
|
}
|
|
15
|
-
export type SynthesisEngine =
|
|
16
|
-
export type TimePitchShiftingMethod =
|
|
17
|
+
export type SynthesisEngine = 'vits' | 'pico' | 'flite' | 'espeak' | 'sam' | 'sapi' | 'msspeech' | 'coqui-server' | 'google-cloud' | 'microsoft-azure' | 'amazon-polly' | 'openai-cloud' | 'elevenlabs' | 'google-translate' | 'microsoft-edge' | 'streamlabs-polly';
|
|
18
|
+
export type TimePitchShiftingMethod = 'sonic' | 'rubberband';
|
|
17
19
|
export interface SynthesisOptions {
|
|
18
20
|
engine?: SynthesisEngine;
|
|
19
21
|
language?: string;
|
|
@@ -31,15 +33,15 @@ export interface SynthesisOptions {
|
|
|
31
33
|
alignment?: API.AlignmentOptions;
|
|
32
34
|
postProcessing?: {
|
|
33
35
|
normalizeAudio?: boolean;
|
|
34
|
-
|
|
35
|
-
|
|
36
|
+
targetPeak?: number;
|
|
37
|
+
maxGainIncrease?: number;
|
|
36
38
|
speed?: number;
|
|
37
39
|
pitch?: number;
|
|
38
40
|
timePitchShiftingMethod?: TimePitchShiftingMethod;
|
|
39
41
|
rubberband?: RubberbandOptions;
|
|
40
42
|
};
|
|
41
43
|
outputAudioFormat?: {
|
|
42
|
-
codec?:
|
|
44
|
+
codec?: 'wav' | 'mp3' | 'opus' | 'm4a' | 'ogg' | 'flac';
|
|
43
45
|
bitrate?: number;
|
|
44
46
|
};
|
|
45
47
|
languageDetection?: API.TextLanguageDetectionOptions;
|
|
@@ -54,6 +56,7 @@ export interface SynthesisOptions {
|
|
|
54
56
|
pitch?: number;
|
|
55
57
|
pitchRange?: number;
|
|
56
58
|
useKlatt?: boolean;
|
|
59
|
+
insertSeparators?: boolean;
|
|
57
60
|
};
|
|
58
61
|
sam?: {
|
|
59
62
|
pitch?: number;
|
|
@@ -88,14 +91,11 @@ export interface SynthesisOptions {
|
|
|
88
91
|
region?: string;
|
|
89
92
|
accessKeyId?: string;
|
|
90
93
|
secretAccessKey?: string;
|
|
91
|
-
pollyEngine?:
|
|
94
|
+
pollyEngine?: 'standard' | 'neural';
|
|
92
95
|
lexiconNames?: string[];
|
|
93
96
|
};
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
stability?: number;
|
|
97
|
-
similarityBoost?: number;
|
|
98
|
-
};
|
|
97
|
+
openAICloud?: OpenAICloudTTSOptions;
|
|
98
|
+
elevenlabs?: ElevenlabsTTSOptions;
|
|
99
99
|
googleTranslate?: {
|
|
100
100
|
tld?: string;
|
|
101
101
|
};
|
|
@@ -137,5 +137,5 @@ export interface SynthesisVoice {
|
|
|
137
137
|
speakerCount?: number;
|
|
138
138
|
packageName?: string;
|
|
139
139
|
}
|
|
140
|
-
export type VoiceGender =
|
|
140
|
+
export type VoiceGender = 'male' | 'female' | 'unknown';
|
|
141
141
|
export declare const synthesisEngines: EngineMetadata[];
|