Kokoro.js v1.2.0: Streaming support (#92)

* Set up JS project

* Finalise JS library

* Update README

* Fix package.json repository url

* Rename package -> `kokoro-js`

* Fix samples in README

* Cleanup README

* Bump `phonemizer` version

* Create web demo

* Run prettier

* Link to model used in demo

* Enable multithreading in HF space demo (~40% faster)

* Add link to demo in README

* Bump to v1.0.1

* Update voices

* Update versions

* Update phonemize JSDoc

* Use updated voice pack

* Update versions

* Update demo (v1.0 & WebGPU support)

* Update README

* Enforce maximum number of tokens

* Update README

* [version] Update to 1.1.1

* Create simple sentence splitter

* Update `npm run test`

* Update API to use sync and async iterators

* Add support for streamed generation in kokoro.js

* Always split on newlines

* Remove debug line

* Improvements

* Add more matching puntuation marks

* Update comments

* nits

* Export TextSplitterStream too

* Update splitter.js

* Update README

* [version] Update to 1.2.0

kokoro.js/README.md

@@ -37,6 +37,44 @@ const audio = await tts.generate(text, {
 audio.save("audio.wav");
 ```
 
+Or if you'd prefer to stream the output, you can do that with:
+
+```js
+import { KokoroTTS, TextSplitterStream } from "kokoro-js";
+
+const model_id = "onnx-community/Kokoro-82M-v1.0-ONNX";
+const tts = await KokoroTTS.from_pretrained(model_id, {
+  dtype: "fp32", // Options: "fp32", "fp16", "q8", "q4", "q4f16"
+  // device: "webgpu", // Options: "wasm", "webgpu" (web) or "cpu" (node).
+});
+
+// First, set up the stream
+const splitter = new TextSplitterStream();
+const stream = tts.stream(splitter);
+(async () => {
+  let i = 0;
+  for await (const { text, phonemes, audio } of stream) {
+    console.log({ text, phonemes });
+    audio.save(`audio-${i++}.wav`);
+  }
+})();
+
+// Next, add text to the stream. Note that the text can be added at different times.
+// For this example, let's pretend we're consuming text from an LLM, one word at a time.
+const text = "Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. It can even run 100% locally in your browser, powered by Transformers.js!";
+const tokens = text.match(/\s*\S+/g);
+for (const token of tokens) {
+  splitter.push(token);
+  await new Promise((resolve) => setTimeout(resolve, 10));
+}
+
+// Finally, close the stream to signal that no more text will be added.
+splitter.close();
+
+// Alternatively, if you'd like to keep the stream open, but flush any remaining text, you can use the `flush` method.
+// splitter.flush();
+```
+
 ## Voices/Samples
 
 > [!TIP]