Skip to content

feat(stt): improve language handling per adapter #2058

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
yujonglee merged 4 commits into from
Dec 2, 2025
Merged

feat(stt): improve language handling per adapter #2058

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
44bd64e
feat(stt): improve language handling per adapter
devin-ai-integration[bot] Dec 2, 2025
fedb7d6
feat(stt): refine language handling per adapter and remove unused LAN…
devin-ai-integration[bot] Dec 2, 2025
f6e0c67
refactors
yujonglee Dec 2, 2025
a376f71
update ui
yujonglee Dec 2, 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
253 changes: 0 additions & 253 deletions apps/desktop/src/components/settings/ai/stt/shared.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,18 +23,6 @@ type Provider = {

export type ProviderId = (typeof PROVIDERS)[number]["id"];

type ProviderModels = {
hyprnote: (typeof PROVIDERS)[0]["models"];
deepgram: (typeof PROVIDERS)[1]["models"];
custom: (typeof PROVIDERS)[2]["models"];
groq: (typeof PROVIDERS)[3]["models"];
fireworks: (typeof PROVIDERS)[4]["models"];
};

type LanguageSupportMap = {
[K in ProviderId]: Partial<Record<ProviderModels[K][number], string[]>>;
};

export const displayModelId = (model: string) => {
if (model === "cloud") {
return "Cloud";
Expand Down Expand Up @@ -142,247 +130,6 @@ export const sttProviderRequiresPro = (providerId: ProviderId) =>
PROVIDERS.find((provider) => provider.id === providerId)?.requiresPro ??
false;

export const LANGUAGE_SUPPORT: LanguageSupportMap = {
hyprnote: {
QuantizedTinyEn: ["en"],
QuantizedSmallEn: ["en"],
"am-parakeet-v2": ["en"],
"am-parakeet-v3": [
"en",
"de",
"es",
"fr",
"nl",
"it",
"da",
"et",
"fi",
"el",
"hu",
"lv",
"lt",
"mt",
"pl",
"pt",
"ro",
"sk",
"sl",
"sv",
"ru",
"uk",
"bg",
"hr",
"cs",
],
"am-whisper-large-v3": [
"af",
"am",
"ar",
"as",
"az",
"ba",
"be",
"bg",
"bn",
"bo",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"fi",
"fo",
"fr",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"ht",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"la",
"lb",
"lo",
"lt",
"lv",
"mg",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"ne",
"nl",
"nn",
"no",
"oc",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"sn",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"tk",
"tl",
"tr",
"tt",
"uk",
"ur",
"uz",
"vi",
"yi",
"yo",
"zh",
],
},
deepgram: {
// https://developers.deepgram.com/docs/models-languages-overview#nova-3
"nova-3-general": [
"en",
"en-US",
"en-AU",
"en-GB",
"en-IN",
"en-NZ",
"de",
"nl",
"sv",
"sv-SE",
"da",
"da-DK",
"es",
"es-419",
"fr",
"fr-CA",
"pt",
"pt-BR",
"pt-PT",
"it",
"tr",
"no",
"id",
],
"nova-3-medical": [
"en",
"en-US",
"en-AU",
"en-CA",
"en-GB",
"en-IE",
"en-IN",
"en-NZ",
],
// https://developers.deepgram.com/docs/models-languages-overview#nova-2
"nova-2-general": [
"bg",
"ca",
"zh",
"zh-CN",
"zh-Hans",
"zh-TW",
"zh-Hant",
"zh-HK",
"cs",
"da",
"da-DK",
"nl",
"en",
"en-US",
"en-AU",
"en-GB",
"en-NZ",
"en-IN",
"et",
"fi",
"nl-BE",
"fr",
"fr-CA",
"de",
"de-CH",
"el",
"hi",
"hu",
"id",
"it",
"ja",
"ko",
"ko-KR",
"lv",
"lt",
"ms",
"no",
"pl",
"pt",
"pt-BR",
"pt-PT",
"ro",
"ru",
"sk",
"es",
"es-419",
"sv",
"sv-SE",
"th",
"th-TH",
"tr",
"uk",
"vi",
],
"nova-2-meeting": ["en", "en-US"],
"nova-2-phonecall": ["en", "en-US"],
"nova-2-finance": ["en", "en-US"],
"nova-2-conversationalai": ["en", "en-US"],
"nova-2-voicemail": ["en", "en-US"],
"nova-2-video": ["en", "en-US"],
"nova-2-medical": ["en", "en-US"],
"nova-2-drivethru": ["en", "en-US"],
"nova-2-automotive": ["en", "en-US"],
"nova-2-atc": ["en", "en-US"],
},
custom: {},
groq: {},
fireworks: {},
};

export const sttModelQueries = {
isDownloaded: (model: SupportedSttModel) =>
queryOptions({
Expand Down
10 changes: 10 additions & 0 deletions apps/desktop/src/components/settings/general/index.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ import * as main from "../../../store/tinybase/main";
import { AppSettingsView } from "./app-settings";
import { MainLanguageView } from "./main-language";
import { Permissions } from "./permissions";
import { SpokenLanguagesView } from "./spoken-languages";

export function SettingsGeneral() {
const value = useConfigValues([
Expand Down Expand Up @@ -134,6 +135,15 @@ export function SettingsGeneral() {
/>
)}
</form.Field>
<form.Field name="spoken_languages">
{(field) => (
<SpokenLanguagesView
value={field.state.value}
onChange={(val) => field.handleChange(val)}
supportedLanguages={SUPPORTED_LANGUAGES}
/>
)}
</form.Field>
</div>
</div>

Expand Down
40 changes: 23 additions & 17 deletions apps/desktop/src/components/settings/general/spoken-languages.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,11 @@ interface SpokenLanguagesViewProps {
supportedLanguages: ISO_639_1_CODE[];
}

function getLanguageName(code: string): string {
const lang = LANGUAGES_ISO_639_1[code as ISO_639_1_CODE];
return lang?.name ?? code;
}

export function SpokenLanguagesView({
value,
onChange,
Expand All @@ -28,14 +33,12 @@ export function SpokenLanguagesView({
return [];
}
const query = languageSearchQuery.toLowerCase();
return supportedLanguages
.filter((langCode) => {
const langName = LANGUAGES_ISO_639_1[langCode].name;
return (
!value.includes(langName) && langName.toLowerCase().includes(query)
);
})
.map((langCode) => LANGUAGES_ISO_639_1[langCode].name);
return supportedLanguages.filter((langCode) => {
const langName = LANGUAGES_ISO_639_1[langCode].name;
return (
!value.includes(langCode) && langName.toLowerCase().includes(query)
);
});
}, [languageSearchQuery, value, supportedLanguages]);

const handleLanguageKeyDown = (e: React.KeyboardEvent<HTMLInputElement>) => {
Expand Down Expand Up @@ -63,7 +66,8 @@ export function SpokenLanguagesView({
languageSelectedIndex >= 0 &&
languageSelectedIndex < filteredLanguages.length
) {
onChange([...value, filteredLanguages[languageSelectedIndex]]);
const selectedCode = filteredLanguages[languageSelectedIndex];
onChange([...value, selectedCode]);
setLanguageSearchQuery("");
setLanguageSelectedIndex(-1);
}
Expand All @@ -90,21 +94,21 @@ export function SpokenLanguagesView({
document.getElementById("language-search-input")?.focus()
}
>
{value.map((lang) => (
{value.map((code) => (
<Badge
key={lang}
key={code}
variant="secondary"
className="flex items-center gap-1 px-2 py-0.5 text-xs bg-muted"
>
{lang}
{getLanguageName(code)}
<Button
type="button"
variant="ghost"
size="sm"
className="h-3 w-3 p-0 hover:bg-transparent ml-0.5"
onClick={(e) => {
e.stopPropagation();
onChange(value.filter((l) => l !== lang));
onChange(value.filter((c) => c !== code));
}}
>
<X className="h-2.5 w-2.5" />
Expand Down Expand Up @@ -147,15 +151,15 @@ export function SpokenLanguagesView({
className="absolute top-full left-0 right-0 mt-1 flex flex-col w-full rounded border border-neutral-200 overflow-hidden bg-white shadow-md z-10 max-h-60 overflow-y-auto"
>
{filteredLanguages.length > 0 ? (
filteredLanguages.map((langName, index) => (
filteredLanguages.map((langCode, index) => (
<button
key={langName}
key={langCode}
id={`language-option-${index}`}
type="button"
role="option"
aria-selected={languageSelectedIndex === index}
onClick={() => {
onChange([...value, langName]);
onChange([...value, langCode]);
setLanguageSearchQuery("");
setLanguageSelectedIndex(-1);
}}
Expand All @@ -168,7 +172,9 @@ export function SpokenLanguagesView({
: "hover:bg-neutral-100",
])}
>
<span className="font-medium truncate">{langName}</span>
<span className="font-medium truncate">
{getLanguageName(langCode)}
</span>
</button>
))
) : (
Expand Down
Loading