feat: user stt language

This commit is contained in:
Timothy Jaeryang Baek
2025-05-24 00:36:30 +04:00
parent 9946dc7b5f
commit baaa285534
14 changed files with 149 additions and 103 deletions
+4 -1
View File
@@ -64,9 +64,12 @@ export const updateAudioConfig = async (token: string, payload: OpenAIConfigForm
return res;
};
export const transcribeAudio = async (token: string, file: File) => {
export const transcribeAudio = async (token: string, file: File, language?: string) => {
const data = new FormData();
data.append('file', file);
if (language) {
data.append('language', language);
}
let error = null;
const res = await fetch(`${AUDIO_API_BASE_URL}/transcriptions`, {
+5 -1
View File
@@ -1,8 +1,12 @@
import { WEBUI_API_BASE_URL } from '$lib/constants';
export const uploadFile = async (token: string, file: File) => {
export const uploadFile = async (token: string, file: File, metadata?: object | null) => {
const data = new FormData();
data.append('file', file);
if (metadata) {
data.append('metadata', JSON.stringify(metadata));
}
let error = null;
const res = await fetch(`${WEBUI_API_BASE_URL}/files/`, {
+13 -2
View File
@@ -17,7 +17,6 @@
import { WEBUI_API_BASE_URL } from '$lib/constants';
import FileItem from '../common/FileItem.svelte';
import Image from '../common/Image.svelte';
import { transcribeAudio } from '$lib/apis/audio';
import FilesOverlay from '../chat/MessageInput/FilesOverlay.svelte';
export let placeholder = $i18n.t('Send a Message');
@@ -160,7 +159,19 @@
try {
// During the file upload, file content is automatically extracted.
const uploadedFile = await uploadFile(localStorage.token, file);
// If the file is an audio file, provide the language for STT.
let metadata = null;
if (
(file.type.startsWith('audio/') || file.type.startsWith('video/')) &&
$settings?.audio?.stt?.language
) {
metadata = {
language: $settings?.audio?.stt?.language
};
}
const uploadedFile = await uploadFile(localStorage.token, file, metadata);
if (uploadedFile) {
console.info('File upload completed:', {
+12 -1
View File
@@ -591,9 +591,20 @@
throw new Error('Created file is empty');
}
// If the file is an audio file, provide the language for STT.
let metadata = null;
if (
(file.type.startsWith('audio/') || file.type.startsWith('video/')) &&
$settings?.audio?.stt?.language
) {
metadata = {
language: $settings?.audio?.stt?.language
};
}
// Upload file to server
console.log('Uploading file to server...');
const uploadedFile = await uploadFile(localStorage.token, file);
const uploadedFile = await uploadFile(localStorage.token, file, metadata);
if (!uploadedFile) {
throw new Error('Server returned null response for file upload');
+12 -2
View File
@@ -27,7 +27,6 @@
createMessagesList,
extractCurlyBraceWords
} from '$lib/utils';
import { transcribeAudio } from '$lib/apis/audio';
import { uploadFile } from '$lib/apis/files';
import { generateAutoCompletion } from '$lib/apis';
import { deleteFileById } from '$lib/apis/files';
@@ -249,8 +248,19 @@
files = [...files, fileItem];
try {
// If the file is an audio file, provide the language for STT.
let metadata = null;
if (
(file.type.startsWith('audio/') || file.type.startsWith('video/')) &&
$settings?.audio?.stt?.language
) {
metadata = {
language: $settings?.audio?.stt?.language
};
}
// During the file upload, file content is automatically extracted.
const uploadedFile = await uploadFile(localStorage.token, file);
const uploadedFile = await uploadFile(localStorage.token, file, metadata);
if (uploadedFile) {
console.log('File upload completed:', {
@@ -153,7 +153,11 @@
await tick();
const file = blobToFile(audioBlob, 'recording.wav');
const res = await transcribeAudio(localStorage.token, file).catch((error) => {
const res = await transcribeAudio(
localStorage.token,
file,
$settings?.audio?.stt?.language
).catch((error) => {
toast.error(`${error}`);
return null;
});
@@ -150,7 +150,11 @@
return;
}
const res = await transcribeAudio(localStorage.token, file).catch((error) => {
const res = await transcribeAudio(
localStorage.token,
file,
$settings?.audio?.stt?.language
).catch((error) => {
toast.error(`${error}`);
return null;
});
+26 -2
View File
@@ -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">{$i18n.t('Speech Playback Speed')}</div>
<div class="flex items-center relative text-xs">
<div class="flex items-center relative text-xs px-3">
<input
type="number"
min="0"
@@ -1,73 +0,0 @@
<script lang="ts">
import { DropdownMenu } from 'bits-ui';
import { getContext } from 'svelte';
import { showSettings } from '$lib/stores';
import { flyAndScale } from '$lib/utils/transitions';
import Dropdown from '$lib/components/common/Dropdown.svelte';
import QuestionMarkCircle from '$lib/components/icons/QuestionMarkCircle.svelte';
import Keyboard from '$lib/components/icons/Keyboard.svelte';
import Map from '$lib/components/icons/Map.svelte';
const i18n = getContext('i18n');
export let showDocsHandler: Function;
export let showShortcutsHandler: Function;
export let onClose: Function = () => {};
</script>
<Dropdown
on:change={(e) => {
if (e.detail === false) {
onClose();
}
}}
>
<slot />
<div slot="content">
<DropdownMenu.Content
class="w-full max-w-[200px] rounded-xl px-1 py-1.5 border border-gray-300/30 dark:border-gray-700/50 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-lg"
sideOffset={4}
side="top"
align="end"
transition={flyAndScale}
>
<DropdownMenu.Item
class="flex gap-2 items-center px-3 py-2 text-sm cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-md"
id="chat-share-button"
on:click={() => {
window.open('https://docs.openwebui.com', '_blank');
}}
>
<QuestionMarkCircle className="size-5" />
<div class="flex items-center">{$i18n.t('Documentation')}</div>
</DropdownMenu.Item>
<!-- Releases -->
<DropdownMenu.Item
class="flex gap-2 items-center px-3 py-2 text-sm cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-md"
id="menu-item-releases"
on:click={() => {
window.open('https://github.com/open-webui/open-webui/releases', '_blank');
}}
>
<Map className="size-5" />
<div class="flex items-center">{$i18n.t('Releases')}</div>
</DropdownMenu.Item>
<DropdownMenu.Item
class="flex gap-2 items-center px-3 py-2 text-sm cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-md"
id="chat-share-button"
on:click={() => {
showShortcutsHandler();
}}
>
<Keyboard className="size-5" />
<div class="flex items-center">{$i18n.t('Keyboard shortcuts')}</div>
</DropdownMenu.Item>
</DropdownMenu.Content>
</div>
</Dropdown>
+12 -1
View File
@@ -276,8 +276,19 @@
files = [...files, fileItem];
try {
// If the file is an audio file, provide the language for STT.
let metadata = null;
if (
(file.type.startsWith('audio/') || file.type.startsWith('video/')) &&
$settings?.audio?.stt?.language
) {
metadata = {
language: $settings?.audio?.stt?.language
};
}
// During the file upload, file content is automatically extracted.
const uploadedFile = await uploadFile(localStorage.token, file);
const uploadedFile = await uploadFile(localStorage.token, file, metadata);
if (uploadedFile) {
console.log('File upload completed:', {
@@ -26,10 +26,7 @@
updateFileFromKnowledgeById,
updateKnowledgeById
} from '$lib/apis/knowledge';
import { transcribeAudio } from '$lib/apis/audio';
import { blobToFile } from '$lib/utils';
import { processFile } from '$lib/apis/retrieval';
import Spinner from '$lib/components/common/Spinner.svelte';
import Files from './KnowledgeBase/Files.svelte';
@@ -158,7 +155,18 @@
knowledge.files = [...(knowledge.files ?? []), fileItem];
try {
const uploadedFile = await uploadFile(localStorage.token, file).catch((e) => {
// If the file is an audio file, provide the language for STT.
let metadata = null;
if (
(file.type.startsWith('audio/') || file.type.startsWith('video/')) &&
$settings?.audio?.stt?.language
) {
metadata = {
language: $settings?.audio?.stt?.language
};
}
const uploadedFile = await uploadFile(localStorage.token, file, metadata).catch((e) => {
toast.error(`${e}`);
return null;
});