feat: user stt language

src/lib/components/chat/Settings/Audio.svelte

@@ -9,6 +9,7 @@
 	import Switch from '$lib/components/common/Switch.svelte';
 	import { round } from '@huggingface/transformers';
 	import Spinner from '$lib/components/common/Spinner.svelte';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
 	const dispatch = createEventDispatcher();
 
 	const i18n = getContext('i18n');
@@ -22,6 +23,7 @@
 	let nonLocalVoices = false;
 
 	let STTEngine = '';
+	let STTLanguage = '';
 
 	let TTSEngine = '';
 	let TTSEngineConfig = {};
@@ -89,6 +91,7 @@
 		responseAutoPlayback = $settings.responseAutoPlayback ?? false;
 
 		STTEngine = $settings?.audio?.stt?.engine ?? '';
+		STTLanguage = $settings?.audio?.stt?.language ?? '';
 
 		TTSEngine = $settings?.audio?.tts?.engine ?? '';
 		TTSEngineConfig = $settings?.audio?.tts?.engineConfig ?? {};
@@ -156,7 +159,8 @@
 		saveSettings({
 			audio: {
 				stt: {
-					engine: STTEngine !== '' ? STTEngine : undefined
+					engine: STTEngine !== '' ? STTEngine : undefined,
+					language: STTLanguage !== '' ? STTLanguage : undefined
 				},
 				tts: {
 					engine: TTSEngine !== '' ? TTSEngine : undefined,
@@ -189,6 +193,26 @@
 						</select>
 					</div>
 				</div>
+
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('Language')}</div>
+
+					<div class="flex items-center relative text-xs px-3">
+						<Tooltip
+							content={$i18n.t(
+								'The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency. Leave blank to automatically detect the language.'
+							)}
+							placement="top"
+						>
+							<input
+								type="text"
+								bind:value={STTLanguage}
+								placeholder={$i18n.t('e.g. en')}
+								class=" text-sm text-right bg-transparent dark:text-gray-300 outline-hidden"
+							/>
+						</Tooltip>
+					</div>
+				</div>
 			{/if}
 
 			<div class=" py-0.5 flex w-full justify-between">
@@ -269,7 +293,7 @@
 			<div class=" py-0.5 flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">{$i18n.t('Speech Playback Speed')}</div>
 
-				<div class="flex items-center relative text-xs">
+				<div class="flex items-center relative text-xs px-3">
 					<input
 						type="number"
 						min="0"