From f94b95d540222749c8a5b04bb78bc10d209aa8bd Mon Sep 17 00:00:00 2001 From: Rotem Dan Date: Wed, 8 May 2024 09:40:51 +0300 Subject: [PATCH] Update docs --- docs/Development.md | 2 +- docs/Server.md | 2 +- docs/Tasklist.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/Development.md b/docs/Development.md index 3e456a9..031033b 100644 --- a/docs/Development.md +++ b/docs/Development.md @@ -82,7 +82,7 @@ Add a `.vscode/launch.json` file to launch the CLI in debug mode: "program": "${workspaceFolder}/dist/cli/CLIStarter.js", "outputCapture": "std", "console": "integratedTerminal", - "runtimeArgs": ["--no-warnings", "--no-experimental-fetch", "--experimental-wasi-unstable-preview1", "--trace-uncaught"], + "runtimeArgs": ["--experimental-wasi-unstable-preview1", "--no-warnings", "--trace-uncaught"], "args": ["speak", "Hello World!", "--debug"] } diff --git a/docs/Server.md b/docs/Server.md index 29b1d46..d8f0606 100644 --- a/docs/Server.md +++ b/docs/Server.md @@ -45,7 +45,7 @@ ws.on("open", async () => { ## Protocol details -The protocol is based on binary WebSocket messages, for both request and response objects. Messages are encoded using the [MessagePack](https://msgpack.org/index.html) encoding scheme. +The protocol is based on binary WebSocket messages, for both request and response objects. Messages are encoded using the [MessagePack](https://msgpack.org) encoding scheme. All messages are objects and have the basic structure: diff --git a/docs/Tasklist.md b/docs/Tasklist.md index ab2573b..8bec526 100644 --- a/docs/Tasklist.md +++ b/docs/Tasklist.md @@ -260,7 +260,7 @@ ### Speech-to-text translation -* Hybrid approach: recognize speech in its language using any recognition model, then translate the resulting transcript using a text-to-text translation engine, and then align the translated transcript to the original one using text-to-text alignment, and map back to the original speech using the recognition timestamps, to get word-level alignment for the translated transcript +* Hybrid approach: recognize speech in its native language using any recognition model, then translate the resulting transcript using a text-to-text translation engine, and then align the translated transcript to the original one using text-to-text alignment, and map back to the original speech using the recognition timestamps, to get word-level alignment for the translated transcript ## Possible new engines or platforms