echogarden 0.8.1 → 0.8.3
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 +1 -1
- package/data/schemas/options.json +50 -62
- package/dist/api/API.d.ts +1 -1
- package/dist/api/API.js +1 -1
- package/dist/api/API.js.map +1 -1
- package/dist/api/Alignment.d.ts +4 -5
- package/dist/api/Alignment.js +10 -9
- package/dist/api/Alignment.js.map +1 -1
- package/dist/api/Common.d.ts +13 -0
- package/dist/api/{Globals.js → Common.js} +1 -1
- package/dist/api/Common.js.map +1 -0
- package/dist/api/Denoising.d.ts +1 -1
- package/dist/api/Recognition.d.ts +2 -6
- package/dist/api/Recognition.js +3 -6
- package/dist/api/Recognition.js.map +1 -1
- package/dist/api/Synthesis.d.ts +2 -6
- package/dist/api/Synthesis.js +2 -2
- package/dist/api/Synthesis.js.map +1 -1
- package/dist/api/Translation.d.ts +4 -7
- package/dist/api/Translation.js +4 -7
- package/dist/api/Translation.js.map +1 -1
- package/dist/api/Vad.d.ts +1 -1
- package/dist/audio/AudioPlayer.d.ts +1 -1
- package/dist/audio/AudioPlayer.js +2 -2
- package/dist/audio/AudioPlayer.js.map +1 -1
- package/dist/cli/CLI.js +14 -12
- package/dist/cli/CLI.js.map +1 -1
- package/dist/denoising/RNNoise.js.map +1 -1
- package/dist/math/VectorMath.d.ts +1 -1
- package/dist/math/VectorMath.js +11 -6
- package/dist/math/VectorMath.js.map +1 -1
- package/dist/nlp/Segmentation.d.ts +1 -2
- package/dist/nlp/Segmentation.js.map +1 -1
- package/dist/recognition/WhisperSTT.d.ts +17 -3
- package/dist/recognition/WhisperSTT.js +43 -15
- package/dist/recognition/WhisperSTT.js.map +1 -1
- package/dist/server/Client.js +2 -2
- package/dist/server/Client.js.map +1 -1
- package/dist/text-language-detection/FastTextLanguageDetection.d.ts +1 -1
- package/dist/text-language-detection/FastTextLanguageDetection.js +1 -1
- package/dist/text-language-detection/FastTextLanguageDetection.js.map +1 -1
- package/dist/utilities/Compression.js.map +1 -1
- package/dist/utilities/FileSystem.js +1 -1
- package/dist/utilities/FileSystem.js.map +1 -1
- package/dist/utilities/PackageManager.js +1 -1
- package/dist/utilities/PackageManager.js.map +1 -1
- package/dist/utilities/TarballMaker.js +1 -1
- package/dist/utilities/TarballMaker.js.map +1 -1
- package/dist/utilities/Timeline.d.ts +2 -1
- package/dist/utilities/Timeline.js +4 -4
- package/dist/utilities/Timeline.js.map +1 -1
- package/docs/Options.md +16 -8
- package/docs/Tasklist.md +3 -1
- package/package.json +4 -4
- package/dist/api/Globals.d.ts +0 -7
- package/dist/api/Globals.js.map +0 -1
package/docs/Tasklist.md
CHANGED
|
@@ -144,6 +144,7 @@
|
|
|
144
144
|
* Full date normalization (e.g. `21 August 2023`, `21 Aug 2023`)
|
|
145
145
|
* Add support for capitalized-only rules, and possibly also all uppercase / all lowercase rules.
|
|
146
146
|
* Support normalizing to graphemes, not only phonemes
|
|
147
|
+
* Add support for multiple words in `precededBy` and `succeededBy`
|
|
147
148
|
* Cache lexicons to avoid parsing the JSON each time it is loaded (this may not be needed for if the file is relatively small)
|
|
148
149
|
* Is it possible to pre-phonemize common words like "the" or is it a bad idea / not necessary?
|
|
149
150
|
* Add support for text preprocessing for all engines that can benefit from it (possibly including cloud engines).
|
|
@@ -237,9 +238,9 @@
|
|
|
237
238
|
### Recognition
|
|
238
239
|
* Low latency recognition mode. Make the partial transcription available as fast as possible
|
|
239
240
|
* Live input / microphone recognition
|
|
240
|
-
* Live vosk alternatives events
|
|
241
241
|
* Implement beam search for Whisper decoder
|
|
242
242
|
* Implement beam search for Silero decoder
|
|
243
|
+
* Live vosk alternatives events
|
|
243
244
|
* Investigate exporting Whisper models to 16-bit quantized ONNX or a mix of 16-bit and 32-bit
|
|
244
245
|
|
|
245
246
|
### Alignment
|
|
@@ -250,6 +251,7 @@
|
|
|
250
251
|
* Predict timing for individual letters (graphemes) based on phoneme timestamps
|
|
251
252
|
|
|
252
253
|
## Documentation
|
|
254
|
+
* Start documenting the developer API, to import the program as a library. At least as experimental. Point to source code for reference.
|
|
253
255
|
|
|
254
256
|
### CLI
|
|
255
257
|
* Document the `serve` command
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "echogarden",
|
|
3
|
-
"version": "0.8.
|
|
3
|
+
"version": "0.8.3",
|
|
4
4
|
"description": "An integrated speech system, providing a set of synthesis, recognition, alignment, and other processing tools, designed to be directly accessible to end-users.",
|
|
5
5
|
"author": "Rotem Dan",
|
|
6
6
|
"license": "GPL-3.0-only",
|
|
@@ -53,8 +53,8 @@
|
|
|
53
53
|
"echogarden": "./dist/cli/CLILauncher.js"
|
|
54
54
|
},
|
|
55
55
|
"dependencies": {
|
|
56
|
-
"@aws-sdk/client-polly": "^3.
|
|
57
|
-
"@aws-sdk/client-transcribe-streaming": "^3.
|
|
56
|
+
"@aws-sdk/client-polly": "^3.377.0",
|
|
57
|
+
"@aws-sdk/client-transcribe-streaming": "^3.377.0",
|
|
58
58
|
"@echogarden/espeak-ng-emscripten": "^0.1.2",
|
|
59
59
|
"@echogarden/fasttext-wasm": "^0.1.0",
|
|
60
60
|
"@echogarden/flite-wasi": "^0.1.1",
|
|
@@ -121,7 +121,7 @@
|
|
|
121
121
|
"@types/msgpack-lite": "^0.1.8",
|
|
122
122
|
"@types/ndarray": "^1.0.11",
|
|
123
123
|
"@types/ndarray-ops": "^1.2.4",
|
|
124
|
-
"@types/node": "^20.4.
|
|
124
|
+
"@types/node": "^20.4.5",
|
|
125
125
|
"@types/recursive-readdir": "^2.2.1",
|
|
126
126
|
"@types/tar": "^6.1.5",
|
|
127
127
|
"@types/ws": "^8.5.5",
|
package/dist/api/Globals.d.ts
DELETED
package/dist/api/Globals.js.map
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"Globals.js","sourceRoot":"","sources":["../../src/api/Globals.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,OAAO,GAAG,YAAY,CAAA"}
|