Skip to content

feat: specify language for AudioToText #266

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.

Sign up for GitHub

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
kyteinsky merged 2 commits into from
Oct 13, 2025
Merged

feat: specify language for AudioToText #266

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e5fb43c
feat: specify language for AudioToText
lukasdotcom Aug 29, 2025
374344a
feat: add user preference to set default language for AudioToText
lukasdotcom Sep 10, 2025
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
2 changes: 2 additions & 0 deletions lib/AppInfo/Application.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,8 @@ class Application extends App implements IBootstrap {
public const MODELS_CACHE_KEY = 'models';
public const MODELS_CACHE_TTL = 60 * 30;

public const AUDIO_TO_TEXT_LANGUAGES = [['en', 'English'], ['zh', '中文'], ['de', 'Deutsch'], ['es', 'Español'], ['ru', 'Русский'], ['ko', '한국어'], ['fr', 'Français'], ['ja', '日本語'], ['pt', 'Português'], ['tr', 'Türkçe'], ['pl', 'Polski'], ['ca', 'Català'], ['nl', 'Nederlands'], ['ar', 'العربية'], ['sv', 'Svenska'], ['it', 'Italiano'], ['id', 'Bahasa Indonesia'], ['hi', 'हिन्दी'], ['fi', 'Suomi'], ['vi', 'Tiếng Việt'], ['he', 'עברית'], ['uk', 'Українська'], ['el', 'Ελληνικά'], ['ms', 'Bahasa Melayu'], ['cs', 'Česky'], ['ro', 'Română'], ['da', 'Dansk'], ['hu', 'Magyar'], ['ta', 'தமிழ்'], ['no', 'Norsk (bokmål / riksmål)'], ['th', 'ไทย / Phasa Thai'], ['ur', 'اردو'], ['hr', 'Hrvatski'], ['bg', 'Български'], ['lt', 'Lietuvių'], ['la', 'Latina'], ['mi', 'Māori'], ['ml', 'മലയാളം'], ['cy', 'Cymraeg'], ['sk', 'Slovenčina'], ['te', 'తెలుగు'], ['fa', 'فارسی'], ['lv', 'Latviešu'], ['bn', 'বাংলা'], ['sr', 'Српски'], ['az', 'Azərbaycanca / آذربايجان'], ['sl', 'Slovenščina'], ['kn', 'ಕನ್ನಡ'], ['et', 'Eesti'], ['mk', 'Македонски'], ['br', 'Brezhoneg'], ['eu', 'Euskara'], ['is', 'Íslenska'], ['hy', 'Հայերեն'], ['ne', 'नेपाली'], ['mn', 'Монгол'], ['bs', 'Bosanski'], ['kk', 'Қазақша'], ['sq', 'Shqip'], ['sw', 'Kiswahili'], ['gl', 'Galego'], ['mr', 'मराठी'], ['pa', 'ਪੰਜਾਬੀ / पंजाबी / پنجابي'], ['si', 'සිංහල'], ['km', 'ភាសាខ្មែរ'], ['sn', 'chiShona'], ['yo', 'Yorùbá'], ['so', 'Soomaaliga'], ['af', 'Afrikaans'], ['oc', 'Occitan'], ['ka', 'ქართული'], ['be', 'Беларуская'], ['tg', 'Тоҷикӣ'], ['sd', 'सिनधि'], ['gu', 'ગુજરાતી'], ['am', 'አማርኛ'], ['yi', 'ייִדיש'], ['lo', 'ລາວ / Pha xa lao'], ['uz', 'Ўзбек'], ['fo', 'Føroyskt'], ['ht', 'Krèyol ayisyen'], ['ps', 'پښتو'], ['tk', 'Туркмен / تركمن'], ['nn', 'Norsk (nynorsk)'], ['mt', 'bil-Malti'], ['sa', 'संस्कृतम्'], ['lb', 'Lëtzebuergesch'], ['my', 'Myanmasa'], ['bo', 'བོད་ཡིག / Bod skad'], ['tl', 'Tagalog'], ['mg', 'Malagasy'], ['as', 'অসমীয়া'], ['tt', 'Tatarça'], ['haw', 'ʻŌlelo Hawaiʻi'], ['ln', 'Lingála'], ['ha', 'هَوُسَ'], ['ba', 'Башҡорт'], ['jw', 'ꦧꦱꦗꦮ'], ['su', 'Basa Sunda'], ['yue', '粤语']];

private IAppConfig $appConfig;

public function __construct(array $urlParams = []) {
Expand Down
10 changes: 9 additions & 1 deletion lib/Service/OpenAiAPIService.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -683,6 +683,8 @@ public function transcribeBase64Mp3(
* @param string|null $userId
* @param File $file
* @param bool $translate
* @param string $model
* @param string $language
* @return string
* @throws Exception
*/
Expand All @@ -691,9 +693,10 @@ public function transcribeFile(
File $file,
bool $translate = false,
string $model = Application::DEFAULT_MODEL_ID,
string $language = 'detect_language',
): string {
try {
$transcriptionResponse = $this->transcribe($userId, $file->getContent(), $translate, $model);
$transcriptionResponse = $this->transcribe($userId, $file->getContent(), $translate, $model, $language);
} catch (NotPermittedException|LockedException|GenericFileException $e) {
$this->logger->warning('Could not read audio file: ' . $file->getPath() . '. Error: ' . $e->getMessage(), ['app' => Application::APP_ID]);
throw new Exception($this->l10n->t('Could not read audio file.'), Http::STATUS_INTERNAL_SERVER_ERROR);
Expand All @@ -707,6 +710,7 @@ public function transcribeFile(
* @param string $audioFileContent
* @param bool $translate
* @param string $model
* @param string $language
* @return string
* @throws Exception
*/
Expand All @@ -715,6 +719,7 @@ public function transcribe(
string $audioFileContent,
bool $translate = true,
string $model = Application::DEFAULT_MODEL_ID,
string $language = 'detect_language',
): string {
if ($this->isQuotaExceeded($userId, Application::QUOTA_TYPE_TRANSCRIPTION)) {
throw new Exception($this->l10n->t('Audio transcription quota exceeded'), Http::STATUS_TOO_MANY_REQUESTS);
Expand All @@ -730,6 +735,9 @@ public function transcribe(
'response_format' => 'verbose_json',
// Verbose needed for extraction of audio duration
];
if ($language !== 'detect_language') {
$params['language'] = $language;
}
$endpoint = $translate ? 'audio/translations' : 'audio/transcriptions';
$contentType = 'multipart/form-data';

Expand Down
27 changes: 23 additions & 4 deletions lib/TaskProcessing/AudioToTextProvider.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,12 @@
use OCA\OpenAi\Service\OpenAiAPIService;
use OCP\Files\File;
use OCP\IAppConfig;
use OCP\IL10N;
use OCP\L10N\IFactory;
use OCP\TaskProcessing\EShapeType;
use OCP\TaskProcessing\ISynchronousProvider;
use OCP\TaskProcessing\ShapeDescriptor;
use OCP\TaskProcessing\ShapeEnumValue;
use OCP\TaskProcessing\TaskTypes\AudioToText;
use Psr\Log\LoggerInterface;
use RuntimeException;
Expand All @@ -25,6 +30,8 @@ public function __construct(
private OpenAiAPIService $openAiAPIService,
private LoggerInterface $logger,
private IAppConfig $appConfig,
private IFactory $l10nFactory,
private IL10N $l,
) {
}

Expand Down Expand Up @@ -53,15 +60,23 @@ public function getInputShapeDefaults(): array {
}

public function getOptionalInputShape(): array {
return [];
return ['language' => new ShapeDescriptor(
$this->l->t('Language'),
$this->l->t('The language of the audio file'),
EShapeType::Enum
)];
}

public function getOptionalInputShapeEnumValues(): array {
return [];
$languageEnumValues = array_map(static function (array $language) {
return new ShapeEnumValue($language[1], $language[0]);
}, Application::AUDIO_TO_TEXT_LANGUAGES);
$detectLanguageEnumValue = new ShapeEnumValue($this->l->t('Detect language'), 'detect_language');
return ['language' => array_merge([$detectLanguageEnumValue], $languageEnumValues)];
}

public function getOptionalInputShapeDefaults(): array {
return [];
return ['language' => 'detect_language'];
}

public function getOutputShapeEnumValues(): array {
Expand All @@ -81,11 +96,15 @@ public function process(?string $userId, array $input, callable $reportProgress)
throw new RuntimeException('Invalid input file');
}
$inputFile = $input['input'];
$language = $input['language'] ?? 'detect_language';
if (!is_string($language)) {
throw new RuntimeException('Invalid language');
}

$model = $this->appConfig->getValueString(Application::APP_ID, 'default_stt_model_id', Application::DEFAULT_MODEL_ID) ?: Application::DEFAULT_MODEL_ID;

try {
$transcription = $this->openAiAPIService->transcribeFile($userId, $inputFile, false, $model);
$transcription = $this->openAiAPIService->transcribeFile($userId, $inputFile, false, $model, $language);
return ['output' => $transcription];
} catch (Exception $e) {
$this->logger->warning('OpenAI\'s Whisper transcription failed with: ' . $e->getMessage(), ['exception' => $e]);
Expand Down
Loading