mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-29 07:05:14 -07:00
add model selection and expanded language support to /transcribe endpoint
Closes #233
This commit is contained in:
@@ -32,6 +32,7 @@ import type {
|
||||
TranscriptionResponse,
|
||||
VoiceProfileCreate,
|
||||
VoiceProfileResponse,
|
||||
WhisperModelSize,
|
||||
} from './types';
|
||||
|
||||
class ApiClient {
|
||||
@@ -318,12 +319,19 @@ class ApiClient {
|
||||
}
|
||||
|
||||
// Transcription
|
||||
async transcribeAudio(file: File, language?: LanguageCode): Promise<TranscriptionResponse> {
|
||||
async transcribeAudio(
|
||||
file: File,
|
||||
language?: LanguageCode,
|
||||
model?: WhisperModelSize,
|
||||
): Promise<TranscriptionResponse> {
|
||||
const formData = new FormData();
|
||||
formData.append('file', file);
|
||||
if (language) {
|
||||
formData.append('language', language);
|
||||
}
|
||||
if (model) {
|
||||
formData.append('model', model);
|
||||
}
|
||||
|
||||
const url = `${this.getBaseUrl()}/transcribe`;
|
||||
const response = await fetch(url, {
|
||||
|
||||
@@ -99,8 +99,11 @@ export interface HistoryListResponse {
|
||||
total: number;
|
||||
}
|
||||
|
||||
export type WhisperModelSize = 'base' | 'small' | 'medium' | 'large' | 'turbo';
|
||||
|
||||
export interface TranscriptionRequest {
|
||||
language?: LanguageCode;
|
||||
model?: WhisperModelSize;
|
||||
}
|
||||
|
||||
export interface TranscriptionResponse {
|
||||
|
||||
@@ -1,10 +1,18 @@
|
||||
import { useMutation } from '@tanstack/react-query';
|
||||
import { apiClient } from '@/lib/api/client';
|
||||
import type { WhisperModelSize } from '@/lib/api/types';
|
||||
import type { LanguageCode } from '@/lib/constants/languages';
|
||||
|
||||
export function useTranscription() {
|
||||
return useMutation({
|
||||
mutationFn: ({ file, language }: { file: File; language?: LanguageCode }) =>
|
||||
apiClient.transcribeAudio(file, language),
|
||||
mutationFn: ({
|
||||
file,
|
||||
language,
|
||||
model,
|
||||
}: {
|
||||
file: File;
|
||||
language?: LanguageCode;
|
||||
model?: WhisperModelSize;
|
||||
}) => apiClient.transcribeAudio(file, language, model),
|
||||
});
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user