Skip to content

server : add Speech Recognition & Synthesis to UI #8679

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 25, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
180 changes: 164 additions & 16 deletions examples/server/public/index.html
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
<html>

<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" />
Expand Down Expand Up @@ -132,12 +131,20 @@
align-items: stretch;
}

.right {
.message-controls {
display: flex;
flex-direction: row;
gap: 0.5em;
justify-content: flex-end;
}
.message-controls > div:nth-child(2) {
display: flex;
flex-direction: column;
gap: 0.5em;
}
.message-controls > div:nth-child(2) > div {
display: flex;
margin-left: auto;
gap: 0.5em;
}

fieldset {
border: none;
Expand Down Expand Up @@ -276,6 +283,7 @@

import { llama } from './completion.js';
import { SchemaConverter } from './json-schema-to-grammar.mjs';

let selected_image = false;
var slot_id = -1;

Expand Down Expand Up @@ -447,6 +455,9 @@

/* END: Support for storing prompt templates and parameters in browsers LocalStorage */

const tts = window.speechSynthesis;
const ttsVoice = signal(null)

const llamaStats = signal(null)
const controller = signal(null)

Expand Down Expand Up @@ -596,8 +607,51 @@
});
}

const SpeechRecognition = window.SpeechRecognition || window.webkitSpeechRecognition;
const talkRecognition = SpeechRecognition ? new SpeechRecognition() : null;
function MessageInput() {
const message = useSignal("")
const message = useSignal("");

const talkActive = useSignal(false);
const sendOnTalk = useSignal(false);
const talkStop = (e) => {
if (e) e.preventDefault();

talkActive.value = false;
talkRecognition?.stop();
}
const talk = (e) => {
e.preventDefault();

if (talkRecognition)
talkRecognition.start();
else
alert("Speech recognition is not supported by this browser.");
}
if(talkRecognition) {
talkRecognition.onstart = () => {
talkActive.value = true;
}
talkRecognition.onresult = (e) => {
if (event.results.length > 0) {
message.value = event.results[0][0].transcript;
if (sendOnTalk.value) {
submit(e);
}
}
}
talkRecognition.onspeechend = () => {
talkStop();
}
}

const ttsVoices = useSignal(tts?.getVoices() || []);
const ttsVoiceDefault = computed(() => ttsVoices.value.find(v => v.default));
if (tts) {
tts.onvoiceschanged = () => {
ttsVoices.value = tts.getVoices();
}
}

const submit = (e) => {
stop(e);
Expand All @@ -624,11 +678,45 @@
value="${message}"
/>
</div>
<div class="right">
<button type="submit" disabled=${generating.value}>Send</button>
<button onclick=${uploadImage}>Upload Image</button>
<button onclick=${stop} disabled=${!generating.value}>Stop</button>
<button onclick=${reset}>Reset</button>
<div class="message-controls">
<div> </div>
<div>
<div>
<button type="submit" disabled=${generating.value || talkActive.value}>Send</button>
<button disabled=${generating.value || talkActive.value} onclick=${uploadImage}>Upload Image</button>
<button onclick=${stop} disabled=${!generating.value}>Stop</button>
<button onclick=${reset}>Reset</button>
</div>
<div>
<a href="#" style="cursor: help;" title="Help" onclick=${e => {
e.preventDefault();
alert(`STT supported by your browser: ${SpeechRecognition ? 'Yes' : 'No'}\n` +
`(TTS and speech recognition are not provided by llama.cpp)\n` +
`Note: STT requires HTTPS to work.`);
}}>[?]</a>
<button disabled=${generating.value} onclick=${talkActive.value ? talkStop : talk}>${talkActive.value ? "Stop Talking" : "Talk"}</button>
<div>
<input type="checkbox" id="send-on-talk" name="send-on-talk" checked="${sendOnTalk}" onchange=${(e) => sendOnTalk.value = e.target.checked} />
<label for="send-on-talk" style="line-height: initial;">Send after talking</label>
</div>
</div>
<div>
<a href="#" style="cursor: help;" title="Help" onclick=${e => {
e.preventDefault();
alert(`TTS supported by your browser: ${tts ? 'Yes' : 'No'}\n(TTS and speech recognition are not provided by llama.cpp)`);
}}>[?]</a>
<label for="tts-voices" style="line-height: initial;">Bot Voice:</label>
<select id="tts-voices" name="tts-voices" onchange=${(e) => ttsVoice.value = e.target.value} style="max-width: 100px;">
<option value="" selected="${!ttsVoice.value}">None</option>
${[
...(ttsVoiceDefault.value ? [ttsVoiceDefault.value] : []),
...ttsVoices.value.filter(v => !v.default),
].map(
v => html`<option value="${v.name}" selected="${ttsVoice.value === v.name}">${v.name} (${v.lang}) ${v.default ? '(default)' : ''}</option>`
)}
</select>
</div>
</div>
</div>
</form>
`
Expand Down Expand Up @@ -659,26 +747,86 @@
}
}, [messages])

const ttsChatLineActiveIx = useSignal(undefined);
const ttsChatLine = (e, ix, msg) => {
if (e) e.preventDefault();

if (!tts || !ttsVoice.value || !('SpeechSynthesisUtterance' in window)) return;

const ttsVoices = tts.getVoices();
const voice = ttsVoices.find(v => v.name === ttsVoice.value);
if (!voice) return;

if (ttsChatLineActiveIx.value !== undefined) {
tts.cancel();
if (ttsChatLineActiveIx.value === ix) {
ttsChatLineActiveIx.value = undefined;
return;
}
}

ttsChatLineActiveIx.value = ix;
let ttsUtter = new SpeechSynthesisUtterance(msg);
ttsUtter.voice = voice;
ttsUtter.onend = e => {
ttsChatLineActiveIx.value = undefined;
};
tts.speak(ttsUtter);
}

const isCompletionMode = session.value.type === 'completion'

// Try play the last bot message
const lastCharChatLinesIxs = useSignal([]);
const lastCharChatLinesIxsOld = useSignal([]);
useEffect(() => {
if (
!isCompletionMode
&& lastCharChatLinesIxs.value.length !== lastCharChatLinesIxsOld.value.length
&& !generating.value
) {
const ix = lastCharChatLinesIxs.value[lastCharChatLinesIxs.value.length - 1];
if (ix !== undefined) {
const msg = messages[ix];
ttsChatLine(null, ix, Array.isArray(msg) ? msg[1].map(m => m.content).join('') : msg);
}

lastCharChatLinesIxsOld.value = structuredClone(lastCharChatLinesIxs.value);
}
}, [generating.value]);

const chatLine = ([user, data], index) => {
let message
const isArrayMessage = Array.isArray(data)
const isArrayMessage = Array.isArray(data);
const text = isArrayMessage ?
data.map(msg => msg.content).join('') :
data;
if (params.value.n_probs > 0 && isArrayMessage) {
message = html`<${Probabilities} data=${data} />`
} else {
const text = isArrayMessage ?
data.map(msg => msg.content).join('') :
data;
message = isCompletionMode ?
text :
html`<${Markdownish} text=${template(text)} />`
}

const fromBot = user && user === '{{char}}';
if (fromBot && !lastCharChatLinesIxs.value.includes(index))
lastCharChatLinesIxs.value.push(index);

if (user) {
return html`<p key=${index}><strong>${template(user)}:</strong> ${message}</p>`
return html`
<div>
<p key=${index}><strong>${template(user)}:</strong> ${message}</p>
${
fromBot && ttsVoice.value
&& html`<button disabled=${generating.value} onclick=${e => ttsChatLine(e, index, text)} aria-label=${ttsChatLineActiveIx.value === index ? 'Pause' : 'Play'}>${ ttsChatLineActiveIx.value === index ? '⏸️' : '▶️' }</div>`
}
</div>
`;
} else {
return isCompletionMode ?
html`<span key=${index}>${message}</span>` :
html`<p key=${index}>${message}</p>`
html`<div><p key=${index}>${message}</p></div>`
}
};

Expand Down
Loading