echogarden 0.0.1 → 0.1.0

package/README.md

@@ -2,4 +2,62 @@
 
 An integrated speech toolbox designed with end-users in mind.
 
-_This is a placeholder for the Echogarden library and command-line tool. It will be published soon._
+* Written in TypeScript, for the Node.js platform
+* Easy to install, run and update
+* Runs on Windows (x64), macOS (x64, ARM64) and Linux (x64)
+* Does not require Python, Docker, or any other system-level dependencies
+* No essential platform-specific binary executables. Engines are ported via WebAssembly or the [ONNX runtime](https://onnxruntime.ai/)
+
+## Feature highlights
+
+* Fast, high-quality offline text-to-speech voices based on the [VITS](https://github.com/jaywalnut310/vits) neural architecture
+* Accurate offline speech recognition using [OpenAI Whisper](https://openai.com/research/whisper) models
+* Supports synthesis and recognition via major cloud providers, including Google, Microsoft and Amazon
+* Word-level timestamps for all synthesis and recognition outputs
+* Speech-to-transcript alignment using dynamic time warping (DTW), and dynamic time warping with recognition assist (DTW-RA) methods
+* Advanced subtitle generation, accounting for sentence and phrase boundaries
+* Can transcribe speech in any one of 98 languages, translated directly to English, and produce near word-level synchronized subtitles
+* Uses NLP for improving TTS pronunciation accuracy on a few engines and languages: adds text normalization (e.g. idiomatic date and currency pronunciation), heteronym disambiguation (based on POS tagging) and user-customizable phonetic lexicons
+* Internal package system to auto-download and install voices, models and other resources, as needed
+* Other features include: language detection (both for audio and text), voice activity detection and speech denoising
+
+## Planned, but not yet
+
+* Real-time, streaming speech recognition
+* WebSocket server API
+* Web-based GUI frontend
+* Browser port for a subset of the API (in particular for the offline TTS models and their dependencies)
+
+## Installation
+
+Ensure you have [Node.js](https://nodejs.org/) `v16.0.0` or later installed.
+
+then:
+```bash
+npm install echogarden -g
+```
+
+Additional tools:
+* [`sox`](https://sourceforge.net/projects/sox/): used for playback and recording only. Auto-installed via an expansion package on Windows and Intel macOS. On Linux and ARM64 macOS, it is recommended to install it via platform package managers like `apt` and `brew`.
+* [`ffmpeg`](https://ffmpeg.org/download.html): used for codec conversions. Auto-installed via an expansion package on Windows, Intel macOS, and Linux. On ARM64 macOS, it is recommended to install it via platform package manager like `brew`, otherwise, much slower `ffmpeg-wasm` would be used.
+
+(hopefully in the future all platforms would be covered using expansion packages)
+
+## Next steps
+
+* [Using the command line interface](docs/CLI.md)
+* [Options reference](docs/Options.md)
+* [Full list of supported engines](docs/Engines.md)
+* [Technical overview and Q&A](docs/Technical.md)
+* [Roadmap](docs/Roadmap.md)
+* [How to help](docs/Development.md)
+
+## Credits
+
+This project consolidates and builds upon the work of [many different individuals and companies](docs/Licenses.md).
+
+Designed and developed by Rotem Dan.
+
+## License
+
+GNU General Public License v3

package/data/lexicons/heteronyms.json

@@ -0,0 +1,674 @@
+{
+	"present": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "p ɹ ɪ z ˈɛ n t"
+				}
+			},
+			"example": "I will present the issue."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "p ɹ ˈɛ z ə n t"
+				}
+			},
+			"example": "I got you a present."
+		}
+	],
+	"read": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɹ ˈiː d"
+				}
+			},
+			"example": "I will read the story."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɹ ˈɛ d"
+				}
+			},
+			"example": "I have read the story."
+		}
+	],
+	"use": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "j ˈuː z"
+				}
+			},
+			"example": "I will use the fork."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "j ˈuː s"
+				}
+			},
+			"example": "There's no use."
+		}
+	],
+	"live": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈɪ v"
+				}
+			},
+			"example": "I will live well."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈaɪ v"
+				}
+			},
+			"example": "It is a live performance."
+		}
+	],
+	"lives": [
+		{
+			"pos": [
+				"VBZ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈɪ v z"
+				}
+			},
+			"example": "She lives vigorously."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈaɪ v z"
+				}
+			},
+			"example": "Their lives are interesting."
+		}
+	],
+	"close": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "k l ˈoʊ z"
+				}
+			},
+			"example": "I will close the door."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "k l ˈoʊ s"
+				}
+			},
+			"example": "It is very close."
+		}
+	],
+	"subject": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "s ʌ b dʒ ˈɛ k t"
+				}
+			},
+			"example": "You must subject to the rules."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "s ˈʌ b dʒ ɛ k t"
+				}
+			},
+			"example": "I understand the subject."
+		}
+	],
+	"subjects": [
+		{
+			"pos": [
+				"VBZ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "s ʌ b dʒ ˈɛ k t s"
+				}
+			},
+			"example": "He subjects them to his silly ideas."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "s ˈʌ b dʒ ɛ k t s"
+				}
+			},
+			"example": "There are many subjects."
+		}
+	],
+	"object": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɑː b dʒ ˈɛ k t"
+				}
+			},
+			"example": "I will object to that ruling."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ˈɑː b dʒ ɛ k t"
+				}
+			},
+			"example": "Here is an object."
+		}
+	],
+	"objects": [
+		{
+			"pos": [
+				"VBZ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɑː b dʒ ˈɛ k t s"
+				}
+			},
+			"example": "She objects to the idea."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ˈɑː b dʒ ɛ k t s"
+				}
+			},
+			"example": "There are lots of objects here."
+		}
+	],
+	"wind": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "w ˈaɪ n d"
+				}
+			},
+			"example": "I know how to wind the engine."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "w ˈɪ n d"
+				}
+			},
+			"example": "The wind is very strong."
+		}
+	],
+	"tear": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "t ˈɛ ɹ"
+				}
+			},
+			"example": "He would tear it."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "t ˈɪ ɹ"
+				}
+			},
+			"example": "She has a tear in her eye."
+		}
+	],
+	"tears": [
+		{
+			"pos": [
+				"VBZ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "t ˈɛɹ z"
+				}
+			},
+			"example": "He always tears it apart."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "t ˈɪɹ z"
+				}
+			},
+			"example": "She has tears in her eyes."
+		}
+	],
+	"minute": [
+		{
+			"pos": [
+				"JJ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "m aɪ n j ˈu t"
+				}
+			},
+			"example": "There's a minute difference between the two."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "m ˈɪ n ɪ t"
+				}
+			},
+			"example": "Wait a minute."
+		}
+	],
+	"inside": [
+		{
+			"pos": [
+				"JJ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ˈɪ n s aɪ d"
+				}
+			},
+			"example": "You can see it on the inside of the box."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɪ n s ˈaɪ d"
+				}
+			},
+			"example": "Please go inside."
+		}
+	],
+	"outside": [
+		{
+			"pos": [
+				"JJ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "aʊ t s ˈaɪ d"
+				}
+			},
+			"example": "This is the outside area."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "aʊ t s ˈaɪ d"
+				}
+			},
+			"example": "Let's go outside."
+		}
+	],
+	"perfect": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "p ɚ f ˈɛ k t"
+				}
+			},
+			"example": "I will perfect my skills."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "p ˈɜː f ɛ k t"
+				}
+			},
+			"example": "This looks perfect."
+		}
+	],
+	"conduct": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "k ə n d ˈʌ k t"
+				}
+			},
+			"example": "I will conduct an experiment."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "k ˈɑː n d ʌ k t"
+				}
+			},
+			"example": "My conduct wasn't very good."
+		}
+	],
+	"desert": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "d ᵻ z ˈɜː t"
+				}
+			},
+			"example": "Please don't desert me."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "d ˈɛ z ɚ t"
+				}
+			},
+			"example": "I like being in the desert."
+		}
+	],
+	"bow": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "b ˈaʊ"
+				}
+			},
+			"example": "Bow to the queen."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "b ˈoʊ"
+				}
+			},
+			"example": "I'm looking to buy a new bow for my cello."
+		}
+	],
+	"row": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɹ ˈoʊ"
+				}
+			},
+			"example": "I ordered them in a row."
+		},
+		{
+			"pos": [
+				"NNP"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɹ ˈoʊ"
+				}
+			},
+			"example": "Row the boat!"
+		},
+		{
+			"pos": [
+				"NNP"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɹ ˈaʊ"
+				}
+			},
+			"example": "There was a row among those people."
+		}
+	],
+	"wound": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "w ˈaʊ n d"
+				}
+			},
+			"example": "I wound the clock several times."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "w ˈuː n d"
+				}
+			},
+			"example": "She got a wound."
+		}
+	],
+	"address": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɐ d ɹ ˈɛ s"
+				}
+			},
+			"example": "I will address the issue."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ˈæ d ɹ ɛ s"
+				}
+			},
+			"example": "What is your address?"
+		}
+	],
+	"entrance": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɛ n t ɹ ˈæ n s"
+				}
+			},
+			"example": "The music will entrance you."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ˈɛ n t ɹ ə n s"
+				}
+			},
+			"example": "Please go to the entrance."
+		}
+	],
+	"produce": [
+		{
+			"pos": [
+				"NNP"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "p ɹ ˈoʊ d uː s"
+				}
+			},
+			"example": "I gave her all the produce."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "p ɹ ə d ˈuː s"
+				}
+			},
+			"example": "I will try to produce more."
+		}
+	],
+	"supposed": [
+		{
+			"pos": [
+				"JJ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "s ə p ˈoʊ z ɪ d"
+				}
+			},
+			"example": "That is the supposed solution."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "s ə p ˈoʊ z d"
+				}
+			},
+			"example": "This was supposed to be somwhere there."
+		}
+	],
+	"learned": [
+		{
+			"pos": [
+				"JJ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈɜː ɹ n ɪ d"
+				}
+			},
+			"example": "She is a very learned person."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈɜː ɹ n d"
+				}
+			},
+			"example": "She learned it."
+		}
+	],
+	"blessed": [
+		{
+			"pos": [
+				"JJ"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "b l ˈɛ s ɪ d"
+				}
+			},
+			"example": "The saints are blessed."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "b l ˈɛ s t"
+				}
+			},
+			"example": "He blessed her."
+		}
+	],
+	"excuse": [
+		{
+			"pos": [
+				"VB"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɛ k s k j ˈuː z"
+				}
+			},
+			"example": "Excuse me? Can you help me?"
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɛ k s k j ˈuː s"
+				}
+			},
+			"example": "There's no excuse for that."
+		}
+	],
+	"lead": [
+		{
+			"pos": [
+				"NNP"
+			],
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈɛ d"
+				}
+			},
+			"example": "Lead is a dangerous substance."
+		},
+		{
+			"pronunciation": {
+				"espeak": {
+					"en-us": "l ˈiː d"
+				}
+			},
+			"example": "You should lead the way."
+		}
+	],
+	"nice": [
+		{
+			"pos": [
+				"NNP"
+			],
+			"case": "capitalized",
+			"pronunciation": {
+				"espeak": {
+					"en-us": "n ˈiː s"
+				}
+			},
+			"example": "I'm flying to Nice."
+		}
+	],
+	"reading": [
+		{
+			"pos": [
+				"NNP"
+			],
+			"case": "capitalized",
+			"pronunciation": {
+				"espeak": {
+					"en-us": "ɹ ˈɛ d ɪ ŋ"
+				}
+			},
+			"example": "I'm driving to Reading."
+		}
+	]
+}